© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52384
    Prev
    Next
    INDEX
    Explanations

    axes, copy, off, require, wind, stunted, shape, children, next, step

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

    control and influence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    0.56
    أ
    0.52
    ване
    0.51
    อ
    0.48
    ア
    0.48
     salaried
    0.48
     поперед
    0.46
    ش
    0.46
    อา
    0.45
    ب
    0.45
    POSITIVE LOGITS
     neurotrans
    0.62
     controll
    0.50
     Metabolism
    0.48
     controlar
    0.47
    制御
    0.47
     multicellular
    0.47
     molecule
    0.47
     modulates
    0.47
     परमाणु
    0.46
     vodu
    0.46
    Activations Density 0.000%

    No Known Activations