© 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. 17219
    Prev
    Next
    INDEX
    Explanations

    . local

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

    negative or limiting phrases

    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
    ’
    0.62
    '
    0.57
    s
    0.52
    re
    0.46
    </strong>
    0.46
    was
    0.45
    rm
    0.43
     representative
    0.42
     Representative
    0.42
     настолько
    0.42
    POSITIVE LOGITS
    ティーク
    0.55
    letzt
    0.54
    gekehrt
    0.54
     lymphatiques
    0.53
    geke
    0.53
    縞
    0.50
     roadblocks
    0.49
    イタリア
    0.49
     arbres
    0.49
     merda
    0.49
    Activations Density 0.000%

    No Known Activations