© 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. 37906
    Prev
    Next
    INDEX
    Explanations

    featured in media

    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
    DER
    -0.82
    ˡ
    -0.82
    Directed
    -0.80
    havn
    -0.79
    伶
    -0.78
    reve
    -0.77
     заявление
    -0.76
    домо
    -0.76
    statement
    -0.76
    ofag
    -0.76
    POSITIVE LOGITS
     featured
    5.72
    featured
    4.28
    Featured
    4.25
     Featured
    3.98
     FEATURE
    2.86
     feature
    2.66
    FEATURE
    2.53
     mentioned
    2.19
     included
    2.09
     features
    2.00
    Activations Density 0.091%

    No Known Activations