© 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. 195893
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    directions

    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
    როს
    0.54
    ikannya
    0.49
    റൽ
    0.49
    ności
    0.48
    ukum
    0.47
    ыргыз
    0.47
    ﻮ
    0.46
    าส
    0.46
    eraient
    0.46
     चाय
    0.46
    POSITIVE LOGITS
     looming
    0.45
     случаи
    0.45
     anden
    0.44
     unreliable
    0.44
     coerce
    0.43
     acon
    0.42
    ane
    0.42
     противопо
    0.42
    想到
    0.42
     firmer
    0.42
    Activations Density 0.000%

    No Known Activations