© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 62932
    Prev
    Next
    INDEX
    Explanations

    extrapolation and extending past trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     h
    0.53
    <0x97>
    0.52
     H
    0.47
     ہ
    0.45
     V
    0.45
    H
    0.44
    𝚅
    0.43
    ห
    0.42
     v
    0.42
    हूं
    0.42
    POSITIVE LOGITS
     extrapolation
    2.67
     extrapolate
    2.66
     extrapol
    2.61
     extrapolated
    2.50
     Ext
    2.14
     extrap
    2.02
    Ext
    1.88
    ext
    1.84
     extradition
    1.84
     extr
    1.80
    Activations Density 0.003%

    No Known Activations