© 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. 180609
    Prev
    Next
    INDEX
    Explanations

    locations and items

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

    Can report to leaders

    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
     সৈনিক
    0.46
     dour
    0.46
    ா
    0.45
     AAP
    0.44
    gana
    0.43
     мес
    0.43
     fordul
    0.43
    濤
    0.43
     armament
    0.42
    ineux
    0.42
    POSITIVE LOGITS
     lại
    0.50
    Cho
    0.48
    EM
    0.47
    Pb
    0.46
    Put
    0.46
    描述
    0.46
    又
    0.46
    1
    0.46
    评价
    0.44
    Spaces
    0.44
    Activations Density 0.000%

    No Known Activations