© 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. 124764
    Prev
    Next
    INDEX
    Explanations

    parcel, about, breasts, courses, limited, north, no

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

    break down how, what

    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
    자리
    0.55
    storeItem
    0.52
    翎
    0.52
    薏
    0.51
    㣫
    0.49
    បន្ថ
    0.48
     가지
    0.47
    боров
    0.47
    ବା
    0.47
    marshalO
    0.47
    POSITIVE LOGITS
    '
    0.64
     clin
    0.62
    ’
    0.61
     on
    0.48
    t
    0.47
     between
    0.46
    re
    0.45
    clin
    0.44
    texas
    0.44
    .
    0.43
    Activations Density 0.000%

    No Known Activations