© 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. 93069
    Prev
    Next
    INDEX
    Explanations

    code parsing and structure

    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
     aforementioned
    -1.02
     Despite
    -1.02
     so
    -1.00
     furthering
    -0.96
    AFFIRMED
    -0.96
     exuberant
    -0.93
    <strong>
    -0.93
    <em>
    -0.93
     prominent
    -0.92
     longstanding
    -0.91
    POSITIVE LOGITS
    apparently
    1.12
     yüzük
    1.03
    thus
    1.02
     jest
    1.00
     акции
    0.99
    various
    0.96
     analiza
    0.96
     sentada
    0.96
    itting
    0.96
    several
    0.96
    Activations Density 0.024%

    No Known Activations