© 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. 210927
    Prev
    Next
    INDEX
    Explanations

    community living

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

    can be

    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
    Norton
    0.55
    的确
    0.47
    णारे
    0.46
    比
    0.46
    Institute
    0.46
    距離
    0.45
    或許
    0.45
    巢
    0.45
    vell
    0.44
    初代
    0.44
    POSITIVE LOGITS
     froze
    0.54
     Uns
    0.49
     Unde
    0.46
     jähr
    0.45
     Frozen
    0.45
     Following
    0.44
     願い
    0.44
     całym
    0.44
     społ
    0.44
     kawa
    0.44
    Activations Density 0.000%

    No Known Activations