© 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. 63146
    Prev
    Next
    INDEX
    Explanations

    book, NVIDIA, SUMMARY, AGPL, GNU

    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
    testify
    -0.81
     '.$
    -0.80
     במה
    -0.79
    Croix
    -0.74
    JScrollPane
    -0.74
     IActionResult
    -0.74
     amarillo
    -0.74
    degree
    -0.73
    ⢀
    -0.73
     decidi
    -0.72
    POSITIVE LOGITS
    其他的
    0.84
    メリ
    0.80
    histle
    0.75
     Juris
    0.75
    ücksich
    0.73
    นาด
    0.73
     Never
    0.73
    淘汰
    0.72
     синте
    0.71
     toks
    0.71
    Activations Density 0.000%

    No Known Activations