© 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. 47517
    Prev
    Next
    INDEX
    Explanations

    get to know

    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
    ícias
    -1.00
    edom
    -0.97
     trám
    -0.95
    üş
    -0.93
     gioia
    -0.92
     mendapat
    -0.91
    ziná
    -0.91
    ograft
    -0.91
     telinga
    -0.88
     zawsze
    -0.88
    POSITIVE LOGITS
     grips
    2.09
     know
    1.89
     see
    1.40
     where
    1.31
     enjoy
    1.17
     work
    1.10
     choose
    1.10
    </b>
    1.09
     the
    1.05
    know
    0.99
    Activations Density 0.011%

    No Known Activations