© 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. 172774
    Prev
    Next
    INDEX
    Explanations

    created, defined, or ranked

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

    manager mentorship, personality, group affiliation

    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
     optimizations
    0.46
    豚
    0.46
     Еўропы
    0.45
     retomar
    0.44
     кафед
    0.44
     proponent
    0.44
    ローブ
    0.43
     диагностики
    0.42
    ้
    0.42
    ोर्ट
    0.42
    POSITIVE LOGITS
    lc
    0.48
    Mega
    0.47
    udiantes
    0.47
    group
    0.46
     խ
    0.46
    uq
    0.45
    Ll
    0.44
    create
    0.44
    assign
    0.44
    Face
    0.44
    Activations Density 0.000%

    No Known Activations