© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117565
    Prev
    Next
    INDEX
    Explanations

    value suivi de chiffres

    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
     there
    -0.98
    чеб
    -0.91
     before
    -0.89
    必要的
    -0.88
     selesai
    -0.85
     denominado
    -0.84
    本章
    -0.83
     अलावा
    -0.82
     sebelum
    -0.82
    Both
    -0.82
    POSITIVE LOGITS
    ひとつ
    0.84
    能够
    0.84
     Nos
    0.84
    脸
    0.82
     ひ
    0.80
     corresponding
    0.78
    α
    0.77
    一つ
    0.76
     jejich
    0.75
     Angriff
    0.75
    Activations Density 0.047%

    No Known Activations