© 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. 31501
    Prev
    Next
    INDEX
    Explanations

    definition and file metadata

    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
    ̦
    -0.88
    ׁ
    -0.82
    oshi
    -0.79
    shimano
    -0.75
    *:
    -0.75
    ⅼ
    -0.75
    ield
    -0.74
    最重要的
    -0.73
    izable
    -0.73
    vP
    -0.73
    POSITIVE LOGITS
    ताओं
    1.03
     NAV
    0.96
     itself
    0.94
    苅
    0.93
    ोड़
    0.91
    balo
    0.91
     toal
    0.90
    angelog
    0.90
     特集
    0.88
    Focusing
    0.87
    Activations Density 0.241%

    No Known Activations