© 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. 38571
    Prev
    Next
    INDEX
    Explanations

    discussion links citing initiatives

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

    you noticed/found/want

    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
    Computational
    0.44
    Facing
    0.44
    髌
    0.44
    ฐาน
    0.43
    Someone
    0.43
    νας
    0.43
     entsch
    0.42
    ถ
    0.41
    passwd
    0.40
     گرفتار
    0.40
    POSITIVE LOGITS
     加入
    0.49
    weight
    0.46
     the
    0.46
     fla
    0.45
     hoops
    0.45
     KH
    0.45
    weights
    0.44
     equaliser
    0.44
     visibly
    0.44
    venor
    0.43
    Activations Density 0.000%

    No Known Activations