© 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. 49047
    Prev
    Next
    INDEX
    Explanations

    responses to forum topics

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

    sex, reflection, however, gather

    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
    system
    0.50
     obviamente
    0.44
     برضو
    0.40
    my
    0.39
    G
    0.39
    ic
    0.39
    devices
    0.38
    ot
    0.38
     ভাই
    0.37
     évidemment
    0.37
    POSITIVE LOGITS
    塭
    0.46
    kWh
    0.40
     প্রকাশ্যে
    0.40
    रेखा
    0.40
    ната
    0.39
    ญา
    0.39
    ავლ
    0.39
    اهای
    0.39
    लेश
    0.38
     செய்வத
    0.38
    Activations Density 0.005%

    No Known Activations