© 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. 77978
    Prev
    Next
    INDEX
    Explanations

    conditional prefixes or terms

    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
     from
    -1.41
     what
    -1.16
     where
    -1.12
     has
    -1.05
     their
    -1.04
     wybrać
    -0.96
    配慮
    -0.94
     like
    -0.93
    予定です
    -0.93
     because
    -0.91
    POSITIVE LOGITS
     prosi
    1.15
     incess
    1.06
    Publié
    1.03
     roba
    1.02
     broadening
    1.02
     suav
    1.02
     reven
    1.02
     expuls
    1.00
     permett
    1.00
     rocha
    0.99
    Activations Density 0.000%

    No Known Activations