© 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. 106934
    Prev
    Next
    INDEX
    Explanations

    isolated components or systems

    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
    Tec
    -0.84
     Phenomen
    -0.77
    YourGuide
    -0.72
    iade
    -0.71
     Tec
    -0.71
    閤
    -0.71
     террито
    -0.70
     mL
    -0.69
    льным
    -0.67
    汰
    -0.67
    POSITIVE LOGITS
     ſi
    0.85
     isola
    0.81
     Isolated
    0.80
     scris
    0.79
     piese
    0.79
    óculos
    0.77
     booths
    0.77
     subi
    0.76
    isolated
    0.76
     Isolation
    0.76
    Activations Density 0.009%

    No Known Activations