© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64722
    Prev
    Next
    INDEX
    Explanations

    code, licenses, photography, songs

    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
     garner
    -0.97
     our
    -0.93
     or
    -0.84
     indicates
    -0.83
    ;
    -0.82
     shitty
    -0.82
    ího
    -0.81
     undoubtedly
    -0.79
     évent
    -0.79
    bumptech
    -0.79
    POSITIVE LOGITS
     ingeniería
    1.02
    batross
    0.90
     HEP
    0.89
    )}$
    0.89
     complication
    0.88
    הפ
    0.87
     happiness
    0.87
     Cæ
    0.85
     frappé
    0.85
     arreglos
    0.84
    Activations Density 0.001%

    No Known Activations