© 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. 22-GEMMASCOPE-RES-131K
    7. 65197
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

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

    The neuron fires on the JSON property name “full_name.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    OMS
    -1.01
     ecles
    -0.98
    pexpr
    -0.94
     الواقع
    -0.93
    ateurs
    -0.93
    雫
    -0.92
    就行了
    -0.90
     dorados
    -0.90
    cestors
    -0.89
    cestor
    -0.89
    POSITIVE LOGITS
     with
    1.59
     and
    1.38
    )+"
    1.09
     after
    1.06
     vermutlich
    1.03
     včetně
    1.02
     titolata
    1.02
     Deshalb
    1.02
     pondering
    1.02
    Gilla
    1.01
    Activations Density 0.000%

    No Known Activations