© 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. 80781
    Prev
    Next
    INDEX
    Explanations

    Income Protection InsuranceSEX eggsCOOK FROMdefeatedcontrolafraid

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

    attention matrix

    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
    ેશન
    0.52
    َّ
    0.50
    ኋ
    0.47
    لك
    0.47
    را
    0.46
    ரியா
    0.46
    ؕ
    0.45
     filesize
    0.45
    ﯽ
    0.45
    стях
    0.44
    POSITIVE LOGITS
    ㄖ
    0.48
     eggs
    0.46
     Eggs
    0.46
    ix
    0.45
     Tons
    0.45
     seks
    0.45
    ಪ
    0.44
     eller
    0.44
     SEX
    0.44
    fowl
    0.44
    Activations Density 0.000%

    No Known Activations