© 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. 45250
    Prev
    Next
    INDEX
    Explanations

    names, titles, and identifiers

    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
     however
    -0.80
     from
    -0.80
     where
    -0.77
     Afrique
    -0.71
    Similar
    -0.71
     so
    -0.71
     available
    -0.71
    NextToken
    -0.70
     Similar
    -0.70
    Available
    -0.70
    POSITIVE LOGITS
     hipote
    0.92
     engran
    0.91
     logement
    0.91
    ///////////
    0.90
     сало
    0.90
     دوست
    0.89
     consé
    0.88
    loyee
    0.85
     medalla
    0.85
    ächtigen
    0.84
    Activations Density 0.067%

    No Known Activations