© 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. 194344
    Prev
    Next
    INDEX
    Explanations

    dates and locations

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

    but however

    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
    붓
    0.53
     суд
    0.52
    efeu
    0.51
     використа
    0.48
    atthena
    0.47
     кою
    0.47
     ट्रेन
    0.46
    कारक
    0.46
    当地
    0.46
     altına
    0.46
    POSITIVE LOGITS
    s
    0.45
     Concise
    0.45
    し
    0.44
    dport
    0.42
    ς
    0.42
    Columbia
    0.42
     concise
    0.42
     freedoms
    0.42
    sans
    0.41
    Assistant
    0.41
    Activations Density 0.000%

    No Known Activations