© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 184902
    Prev
    Next
    INDEX
    Explanations

    formal language components

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

    listen without judgment

    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
     хірур
    0.54
    キャンセル
    0.49
    itochond
    0.48
     (#{
    0.44
     საჭ
    0.44
    igeons
    0.44
    ಸ್ತು
    0.44
     স্বাদ
    0.44
     લાભ
    0.43
    śli
    0.42
    POSITIVE LOGITS
     con
    0.46
     relation
    0.44
     vis
    0.42
    之
    0.42
     dass
    0.41
    ويل
    0.41
     otra
    0.40
    大地
    0.40
    of
    0.40
     किम
    0.40
    Activations Density 0.001%

    No Known Activations