© 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. 29567
    Prev
    Next
    INDEX
    Explanations

    ACCESS

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

    multiplication and division

    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
    就需要
    0.46
     தேவை
    0.46
    해야
    0.44
    ваме
    0.44
    そらく
    0.43
     자체가
    0.43
    Ა
    0.42
    มาจาก
    0.42
     надо
    0.42
     문제가
    0.42
    POSITIVE LOGITS
    <0xE8>
    0.45
    ចែកចាយ
    0.41
     mes
    0.41
    кур
    0.39
     dazz
    0.39
     deport
    0.39
    EOUS
    0.39
     delectable
    0.38
     الح
    0.38
     boca
    0.38
    Activations Density 0.000%

    No Known Activations