© 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. 84015
    Prev
    Next
    INDEX
    Explanations

    lineage, exist, wearing, blooded

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

    detecting misinformation or errors

    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
    書店
    0.50
     SIT
    0.46
    льної
    0.46
     ハンド
    0.45
    Plain
    0.45
    pojo
    0.45
    開
    0.44
     обеспечить
    0.44
    <unused36>
    0.43
    ecd
    0.43
    POSITIVE LOGITS
     važ
    0.46
    uroy
    0.44
     calves
    0.43
     sheath
    0.42
     skis
    0.42
     stresses
    0.42
     attaches
    0.42
    ُر
    0.41
     therefor
    0.40
     reefs
    0.40
    Activations Density 0.000%

    No Known Activations