© 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. 175209
    Prev
    Next
    INDEX
    Explanations

    lifelong nursing, jewelry store, switch battery

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

    legal issues or conditions

    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
     an
    0.59
     to
    0.55
     be
    0.51
     plasm
    0.50
     Leiden
    0.48
    projects
    0.47
     zijn
    0.46
     a
    0.46
    fragen
    0.46
     undervalued
    0.46
    POSITIVE LOGITS
     斜
    0.53
     椅
    0.49
     单位
    0.48
    रल
    0.48
     食品
    0.48
     無料
    0.48
     Số
    0.47
     政府
    0.46
    ずれ
    0.45
     品質
    0.44
    Activations Density 0.000%

    No Known Activations