© 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. 62962
    Prev
    Next
    INDEX
    Explanations

    how followed by description

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

    how followed by manner or degree

    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
     achieve
    0.69
    會
    0.61
     Việc
    0.60
    の説明
    0.59
     Você
    0.59
    \
    0.59
    ეგის
    0.58
    というのは
    0.57
    $,
    0.56
    จึง
    0.56
    POSITIVE LOGITS
    an
    0.61
    ized
    0.60
    ان
    0.59
    ceded
    0.59
    soever
    0.58
    led
    0.57
    n
    0.57
    itched
    0.55
    r
    0.54
    eils
    0.54
    Activations Density 0.055%

    No Known Activations