© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 37606
    Prev
    Next
    INDEX
    Explanations

    glacier, ice, snow

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

    glacial ice melt

    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
    ตะ
    0.50
    ्लो
    0.45
    avacanam
    0.45
    jahteraan
    0.44
    amental
    0.44
     беремен
    0.44
    咪
    0.43
    欝
    0.43
    枣
    0.43
    唒
    0.43
    POSITIVE LOGITS
     glacier
    1.11
     glaciers
    1.10
     ice
    1.07
     thawing
    1.05
     Gletscher
    1.04
    冰
    1.02
     Ice
    1.00
     thaw
    1.00
     glacial
    0.98
     melting
    0.96
    Activations Density 0.084%

    No Known Activations