© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74157
    Prev
    Next
    INDEX
    Explanations

    bend starts, flash rate, turns in

    np_acts-logits-general · gemini-2.5-flash-lite

    feature engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     research
    0.46
     download
    0.45
    CLUS
    0.45
    食用
    0.44
    使用
    0.42
    大量
    0.42
     PLANTS
    0.42
     》
    0.42
     Web
    0.41
     使用
    0.40
    POSITIVE LOGITS
    लिन
    0.53
    atians
    0.50
     hoş
    0.50
     dejó
    0.48
    atir
    0.47
     черно
    0.47
    ati
    0.46
    ėj
    0.46
    𝕟
    0.46
     terça
    0.46
    Activations Density 0.000%

    No Known Activations