© 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. 112089
    Prev
    Next
    INDEX
    Explanations

    website and our

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

    fraternal twins, daughter, plantains, diversity, collects data

    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
    state
    0.63
    pl
    0.61
    AT
    0.59
    name
    0.56
    scope
    0.53
    ax
    0.51
    kv
    0.51
    Q
    0.49
    value
    0.48
    StateManager
    0.48
    POSITIVE LOGITS
     그러면
    0.57
    螫
    0.52
     결
    0.52
     PLANTS
    0.51
    QAry
    0.51
     더
    0.50
     اسرائیل
    0.49
     강화
    0.49
    tFileInputExcel
    0.49
     ㅣ
    0.49
    Activations Density 0.000%

    No Known Activations