© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44469
    Prev
    Next
    INDEX
    Explanations

    animal enclosures

    np_acts-logits-general · gemini-2.5-flash-lite

    animal containment structures such as pens, cages, enclosures, or corrals.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on terms that denote animal enclosures or confinement (e.g. pen, caged, corral).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     that
    -1.60
     Suomessa
    -1.36
    寕
    -1.34
    一旁的
    -1.29
    Britannique
    -1.26
     ataupun
    -1.24
     marinho
    -1.21
    佉
    -1.20
    3
    -1.20
    嘴巴
    -1.20
    POSITIVE LOGITS
     where
    1.55
     memperbaiki
    1.48
     meningkatkan
    1.32
     WITH
    1.29
     mendorong
    1.28
    ♔
    1.27
    jenigen
    1.25
     contains
    1.24
    rafty
    1.24
    vedad
    1.23
    Activations Density 0.020%

    No Known Activations