© 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. 78598
    Prev
    Next
    INDEX
    Explanations

    matriarch

    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
     permisos
    -0.75
     Highlander
    -0.75
     शाम
    -0.74
     assemblages
    -0.71
    TOMS
    -0.69
    SIR
    -0.68
    #"
    -0.68
     fornecer
    -0.68
     STATION
    -0.68
    телем
    -0.68
    POSITIVE LOGITS
    𝔬
    0.76
     Able
    0.74
    畠
    0.71
    virtual
    0.69
     pron
    0.69
    
    0.69
     invisible
    0.67
     matri
    0.67
     colorful
    0.66
     Gute
    0.66
    Activations Density 0.065%

    No Known Activations