© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 73276
    Prev
    Next
    INDEX
    Explanations

    introducing conditions or questions

    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_10/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
     in
    -2.03
    ");
    
    -1.64
    <i>
    -1.55
     {};
    
    -1.45
     and
    -1.45
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.44
     );
    
    -1.40
    la
    -1.40
    ↵↵↵↵↵
    -1.38
    _
    -1.36
    POSITIVE LOGITS
     that
    2.08
    hasilkan
    1.81
    これだけ
    1.80
     ascenso
    1.68
     pasillo
    1.64
    都已经
    1.63
    色々と
    1.59
     Hinblick
    1.59
    それだけ
    1.59
     deliciosos
    1.58
    Activations Density 0.034%

    No Known Activations