© 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. 80751
    Prev
    Next
    INDEX
    Explanations

    can followed by verbs

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

    can find information

    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
    can
    0.55
    提供
    0.54
    provide
    0.52
     provide
    0.50
     vytvá
    0.49
     można
    0.48
    could
    0.47
    :
    0.46
    你不
    0.44
    easily
    0.44
    POSITIVE LOGITS
    ্তার
    0.50
    idamente
    0.48
     처음
    0.47
     ഉൾ
    0.46
     உள்ப
    0.45
     antiguo
    0.44
     கூறிய
    0.44
     Оно
    0.44
     எங்கள்
    0.44
     nostro
    0.43
    Activations Density 0.080%

    No Known Activations