© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58702
    Prev
    Next
    INDEX
    Explanations

    code delimters and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nejšie
    -0.70
    SDR
    -0.70
    étit
    -0.68
    ⛥
    -0.67
     Rede
    -0.66
     Didi
    -0.66
     übertragen
    -0.65
     Imo
    -0.65
     Reve
    -0.65
    Rede
    -0.64
    POSITIVE LOGITS
    ردد
    0.73
    你可以
    0.64
     shackles
    0.63
    calculus
    0.63
     densité
    0.63
    uwa
    0.62
     axiom
    0.62
    лә
    0.61
     fits
    0.61
     г
    0.60
    Activations Density 0.075%

    No Known Activations