© 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. 21720
    Prev
    Next
    INDEX
    Explanations

    words following specific words

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

    final state or action

    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
    意義
    0.55
    カナ
    0.51
    意思
    0.44
     radii
    0.44
    を書
    0.43
    利
    0.43
    試料
    0.43
    印
    0.43
    坎
    0.43
    楢
    0.43
    POSITIVE LOGITS
    uf
    0.49
    ufu
    0.48
     Installation
    0.47
    ufl
    0.47
    hile
    0.46
    ‌.
    0.46
     Usted
    0.46
    ু
    0.45
    uğu
    0.45
    illent
    0.45
    Activations Density 0.000%

    No Known Activations