© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81730
    Prev
    Next
    INDEX
    Explanations

    <h1> headings

    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
     any
    -1.63
     at
    -1.63
     could
    -1.56
     after
    -1.55
     took
    -1.52
     had
    -1.48
     came
    -1.48
     as
    -1.48
     when
    -1.48
     for
    -1.47
    POSITIVE LOGITS
     VERY
    1.98
    </h4>
    1.86
     AMAZING
    1.75
     REALLY
    1.60
     !!!!
    1.56
     flamboyant
    1.55
     magnific
    1.53
     deliciously
    1.53
     luscious
    1.48
     quintessential
    1.48
    Activations Density 0.016%

    No Known Activations