© 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. 57097
    Prev
    Next
    INDEX
    Explanations

    copyright, license, warranty

    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
    凌天
    -0.85
     найбіль
    -0.75
    [-\
    -0.74
    它們
    -0.74
    ظة
    -0.74
    Prize
    -0.73
    tivität
    -0.73
     деревьев
    -0.70
     Perseverance
    -0.69
    Какво
    -0.68
    POSITIVE LOGITS
    味わ
    0.79
    gena
    0.79
     resolves
    0.76
     gf
    0.75
     муль
    0.70
     tensor
    0.69
    通
    0.69
     qualifying
    0.69
     CONTROL
    0.69
    zt
    0.68
    Activations Density 0.048%

    No Known Activations