© 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. 179102
    Prev
    Next
    INDEX
    Explanations

    archived from

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

    ice cube

    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
     继续
    0.45
    事务
    0.44
    诸
    0.44
    邻
    0.43
    文字
    0.42
     文字
    0.42
     살펴
    0.41
     정
    0.40
    тивов
    0.40
    श्रे
    0.39
    POSITIVE LOGITS
     adsorbed
    0.51
    reszt
    0.49
     eluted
    0.49
     nedeniyle
    0.48
     pathogens
    0.48
     nedeni
    0.48
     smoked
    0.48
    )}"
    0.47
     evaporated
    0.47
    ）,
    0.47
    Activations Density 0.001%

    No Known Activations