© 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. 107040
    Prev
    Next
    INDEX
    Explanations

    actors' names

    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
    мови
    -0.78
    齦
    -0.77
     pudieron
    -0.75
    alert
    -0.74
     acontecimientos
    -0.73
    хваты
    -0.73
     wollten
    -0.72
     from
    -0.70
    lesi
    -0.70
     circunstancias
    -0.70
    POSITIVE LOGITS
     Starr
    1.30
     upcoming
    0.97
    主演
    0.96
    arrer
    0.95
     starred
    0.91
    いだ
    0.85
     starter
    0.85
     essays
    0.84
    HBO
    0.83
     essay
    0.82
    Activations Density 0.020%

    No Known Activations