© 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. 194183
    Prev
    Next
    INDEX
    Explanations

    following quantities and situations

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

    labels, definitions, and code arguments

    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
    na
    0.52
    Warranty
    0.50
    G
    0.50
    N
    0.49
    Č
    0.49
    Cnt
    0.49
    se
    0.48
    BSA
    0.47
    K
    0.47
    予
    0.47
    POSITIVE LOGITS
     принял
    0.58
     කොට
    0.52
     বাবার
    0.51
     выступи
    0.50
     سایټ
    0.49
     말투
    0.49
     தாக்க
    0.49
     gazed
    0.48
     healthiest
    0.48
     каттоо
    0.47
    Activations Density 0.000%

    No Known Activations