© 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. 34-GEMMASCOPE-RES-131K
    7. 107940
    Prev
    Next
    INDEX
    Explanations

    words ending in -dized

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

    The neuron responds to numeric tokens (e.g. years, figures, and other digit‐based items).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    赊
    -1.20
    んだから
    -1.16
     impone
    -1.13
     clearness
    -1.11
     fusca
    -1.08
     overcrow
    -1.05
    otriva
    -1.02
     contenta
    -0.98
     fresa
    -0.97
    転車
    -0.96
    POSITIVE LOGITS
     penultimate
    1.15
     conjecture
    1.13
     ethereal
    1.12
    spyOn
    1.10
     circum
    1.05
     plethora
    1.05
     juxta
    1.05
     facade
    1.05
     jest
    1.03
     mun
    1.00
    Activations Density 0.089%

    No Known Activations