© 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. 44735
    Prev
    Next
    INDEX
    Explanations

    ha

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

    terms, promises, adherence

    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
     మొద
    0.47
    朢
    0.47
     eingesetzt
    0.46
    mara
    0.45
    irme
    0.44
    alog
    0.43
    ალაქ
    0.43
     আল
    0.43
    餞
    0.43
    ines
    0.43
    POSITIVE LOGITS
     gotta
    0.53
     trivia
    0.50
     MAKE
    0.46
    STANDING
    0.45
    standing
    0.44
    딛
    0.44
     defibr
    0.43
     genital
    0.43
     Inferno
    0.43
     realizing
    0.43
    Activations Density 0.003%

    No Known Activations