© 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. 130746
    Prev
    Next
    INDEX
    Explanations

    wound along

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

    relative positional indicators

    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
    हायला
    0.55
    banana
    0.52
    iously
    0.50
    bicyclo
    0.49
    tuned
    0.49
    titled
    0.49
    䥑
    0.48
    バン
    0.48
     আস্তে
    0.47
    crates
    0.47
    POSITIVE LOGITS
     principal
    0.43
     bez
    0.41
     চূড়ান্ত
    0.41
     nM
    0.41
     relative
    0.40
     final
    0.39
    ’
    0.39
     iterable
    0.39
     bullpen
    0.39
     Bake
    0.38
    Activations Density 0.000%

    No Known Activations