© 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. 107045
    Prev
    Next
    INDEX
    Explanations

    code, scientific, Q&A

    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
    řejmě
    -0.83
     Стали
    -0.81
    Törté
    -0.76
    ungal
    -0.76
     Paroles
    -0.75
     bifurcation
    -0.75
    рус
    -0.75
     lørdag
    -0.75
     Reported
    -0.74
    
    -0.74
    POSITIVE LOGITS
     GFP
    1.16
    GFP
    0.82
     sakin
    0.81
     consumo
    0.79
    keypress
    0.78
    atomic
    0.73
    Apenas
    0.73
    idr
    0.73
    getSubject
    0.73
    北方
    0.72
    Activations Density 0.064%

    No Known Activations