© 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. 78553
    Prev
    Next
    INDEX
    Explanations

    characterization and preparation

    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
     hongos
    -0.81
     Ketua
    -0.80
     mestre
    -0.77
    པ
    -0.74
     scolas
    -0.74
     Sakit
    -0.73
    龕
    -0.71
     COMPANY
    -0.70
     Hester
    -0.69
     culturale
    -0.69
    POSITIVE LOGITS
     explo
    0.85
     deposits
    0.83
     explosive
    0.83
     пиро
    0.80
    鄞
    0.78
     deposit
    0.76
    endpush
    0.75
    inherits
    0.75
    explo
    0.73
    twimg
    0.73
    Activations Density 0.009%

    No Known Activations