© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108965
    Prev
    Next
    INDEX
    Explanations

    rapporteur, report, speaker

    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
    塗
    -0.71
    Recipient
    -0.70
     Hanuman
    -0.68
     произведения
    -0.68
     گذاری
    -0.66
     drinker
    -0.66
     एस
    -0.65
    νο
    -0.65
    дов
    -0.65
     Torino
    -0.65
    POSITIVE LOGITS
     rapp
    3.20
     Rapp
    2.81
    Rapp
    2.61
     rapporte
    2.20
    rapp
    2.19
    Rap
    1.22
     rel
    1.20
     rap
    1.20
    Reporter
    1.20
     rapping
    1.15
    Activations Density 0.075%

    No Known Activations