© 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. 195952
    Prev
    Next
    INDEX
    Explanations

    acknowledged Thursday, attempt their

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

    how things are said

    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
    鳳
    0.54
    finding
    0.53
    豹
    0.53
    ཆ
    0.50
    ެއް
    0.50
    全く
    0.49
    φος
    0.49
    豐
    0.48
     afresh
    0.46
    كد
    0.46
    POSITIVE LOGITS
     He
    0.50
     FHD
    0.50
     hunk
    0.48
    rom
    0.48
    itos
    0.48
     घूमने
    0.47
     ROB
    0.46
     Bk
    0.45
     K
    0.45
     ROM
    0.44
    Activations Density 0.000%

    No Known Activations