© 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. 53089
    Prev
    Next
    INDEX
    Explanations

    souls, container, fully, tile, Near

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

    reproductive health

    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
    端
    0.49
    Linkedin
    0.47
     refinance
    0.47
    潾
    0.46
    優
    0.46
    کول
    0.46
     کاهش
    0.45
    ulis
    0.45
    ポスト
    0.45
    メモ
    0.44
    POSITIVE LOGITS
    mselves
    0.54
     insulted
    0.52
     apologised
    0.49
     TOKEN
    0.49
    l
    0.48
     affixed
    0.47
    lof
    0.47
    blich
    0.46
    olok
    0.46
     youths
    0.46
    Activations Density 0.000%

    No Known Activations