© 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. 163243
    Prev
    Next
    INDEX
    Explanations

    counting years

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

    production and ongoing

    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
    嫨
    0.59
    鍛
    0.51
    物
    0.49
    蜼
    0.48
    迠
    0.47
    퇴
    0.47
    తున్నారు
    0.47
     doigts
    0.47
    省
    0.47
    ?</
    0.46
    POSITIVE LOGITS
    publication
    0.53
    composition
    0.50
    uy
    0.49
    read
    0.49
    ids
    0.48
    refer
    0.47
    seudo
    0.47
    ilya
    0.47
    icro
    0.47
    arranged
    0.47
    Activations Density 0.002%

    No Known Activations