© 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. 159525
    Prev
    Next
    INDEX
    Explanations

    Christmas Coloring Pages

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

    temporary states or changes

    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
     explored
    0.50
    দ্বন্দ্ব
    0.46
     compuesta
    0.45
    探索
    0.45
     thrills
    0.44
     conocida
    0.44
    珮
    0.44
     comp
    0.44
    IFIER
    0.44
     piena
    0.43
    POSITIVE LOGITS
    sion
    0.49
    smallskip
    0.49
    رے
    0.48
    ɢ
    0.46
    ålet
    0.46
    gradle
    0.45
     Adem
    0.45
     рэгістрацыі
    0.45
    reement
    0.44
     Renaud
    0.44
    Activations Density 0.000%

    No Known Activations