© 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. 30765
    Prev
    Next
    INDEX
    Explanations

    what it takes

    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
     damska
    -0.80
    長
    -0.79
     PLO
    -0.79
    IRI
    -0.77
     consumi
    -0.75
    மே
    -0.74
    longest
    -0.74
     Cardiology
    -0.73
     限定
    -0.73
    周
    -0.72
    POSITIVE LOGITS
     takes
    1.91
    takes
    1.39
    Takes
    1.31
     Takes
    1.30
     take
    1.08
    take
    0.90
     required
    0.90
    Take
    0.88
     Required
    0.85
    效益
    0.85
    Activations Density 0.016%

    No Known Activations