© 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. 93644
    Prev
    Next
    INDEX
    Explanations

    special identifiers or foreign words

    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
     ignoring
    -0.84
     mitos
    -0.84
     comuni
    -0.81
     italiana
    -0.80
     nice
    -0.78
     before
    -0.77
     calo
    -0.76
    主催
    -0.76
     trying
    -0.75
     incorporating
    -0.75
    POSITIVE LOGITS
    gres
    0.88
     désert
    0.86
     znac
    0.85
    <![
    0.82
    ishments
    0.81
     teneur
    0.80
    tically
    0.80
    ляется
    0.80
    Legături
    0.80
    }$.
    0.79
    Activations Density 0.000%

    No Known Activations