© 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. 57298
    Prev
    Next
    INDEX
    Explanations

    section numbers or 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
    Khu
    -0.75
    ELM
    -0.73
    Walnut
    -0.72
    Virgil
    -0.71
    setNum
    -0.71
    jutkan
    -0.68
    ʈ
    -0.68
    OCT
    -0.67
     hysteria
    -0.67
    ידות
    -0.67
    POSITIVE LOGITS
     Pflege
    0.77
     kaart
    0.76
     музыки
    0.74
    ផ
    0.74
     ersten
    0.73
     accountability
    0.73
    Bul
    0.72
     Alexandre
    0.70
     Kartoffeln
    0.70
     Eindruck
    0.69
    Activations Density 0.068%

    No Known Activations