© 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. 31439
    Prev
    Next
    INDEX
    Explanations

    code structures and file paths

    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
     another
    -0.97
     certainly
    -0.93
     should
    -0.88
    のですね
    -0.86
     referente
    -0.83
     attiva
    -0.83
     each
    -0.83
     entera
    -0.83
     those
    -0.82
    elementAt
    -0.82
    POSITIVE LOGITS
     alltid
    1.13
     masih
    1.04
     incont
    1.01
     avantaj
    1.00
    ～」
    1.00
     parfois
    0.97
     désormais
    0.97
     souvent
    0.96
     المتحدة
    0.94
     faciliter
    0.94
    Activations Density 0.004%

    No Known Activations