© 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. 105142
    Prev
    Next
    INDEX
    Explanations

    actions describing someone's role

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

    hauptsächlich, principally, correctly

    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
     и
    0.60
    και
    0.56
     และ
    0.54
    और
    0.53
    và
    0.53
     आणि
    0.52
     και
    0.51
    잊
    0.51
     और
    0.50
     અને
    0.50
    POSITIVE LOGITS
     müs
    0.43
     především
    0.42
     požad
    0.42
     lediglich
    0.42
     corretamente
    0.42
     bulunan
    0.41
     فرض
    0.41
     Gr
    0.40
     Laub
    0.39
     décrit
    0.39
    Activations Density 0.004%

    No Known Activations