© 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. 47477
    Prev
    Next
    INDEX
    Explanations

    Paul McCartney

    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
     so
    -0.92
    ására
    -0.85
    -
    -0.82
     ballerina
    -0.82
     截
    -0.81
     だっ
    -0.81
     grand
    -0.81
     İç
    -0.80
     Int
    -0.79
     أبي
    -0.79
    POSITIVE LOGITS
     '*':
    1.25
    cologist
    1.14
     colorear
    1.14
    elegante
    1.09
     опас
    1.08
     '+':
    1.06
     は
    1.05
    rivial
    1.04
    !!!!!!
    1.02
    ſelf
    1.00
    Activations Density 0.011%

    No Known Activations