© 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. 224362
    Prev
    Next
    INDEX
    Explanations

    post haste

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

    long-term relationships and monitoring

    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
    ThoughtData
    0.50
    َب
    0.49
     ká
    0.48
     Kā
    0.48
    т
    0.47
    เง
    0.47
     يش
    0.47
     Timurtaş
    0.46
     Gründe
    0.45
     Fourteenth
    0.45
    POSITIVE LOGITS
    ess
    0.57
    db
    0.54
    oline
    0.52
    (
    0.52
    ruct
    0.52
    esses
    0.51
    lib
    0.50
    ock
    0.50
    web
    0.50
    codes
    0.50
    Activations Density 0.000%

    No Known Activations