© 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. 64213
    Prev
    Next
    INDEX
    Explanations

    a, b, c, d lists followed by . or )

    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
    ごちそう
    -1.05
    久し
    -1.00
    ウチ
    -0.98
    ごめんなさい
    -0.94
    ようで
    -0.93
    çok
    -0.92
     retours
    -0.91
    感じで
    -0.91
    ómago
    -0.91
    namely
    -0.91
    POSITIVE LOGITS
     D
    1.01
     e
    0.96
    h
    0.91
    j
    0.91
    d
    0.91
    f
    0.90
     same
    0.89
     C
    0.87
     i
    0.85
     f
    0.85
    Activations Density 0.018%

    No Known Activations