© 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. 134059
    Prev
    Next
    INDEX
    Explanations

    may issue, attach your, keynote lectures

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

    husband, ownership, sink, removing, stunning

    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
    warn
    0.46
     aimed
    0.46
     حمد
    0.44
     waitress
    0.41
     glamorous
    0.41
     TSS
    0.41
     Journalists
    0.40
    .
    0.40
    ый
    0.40
     flavoured
    0.40
    POSITIVE LOGITS
    𝔸
    0.52
    지에
    0.48
    🧺
    0.46
    فی
    0.45
     পরম্প
    0.45
     ಪುಸ್ತಕ
    0.44
    ไม้
    0.44
    یم
    0.44
     علی
    0.44
    𝗞
    0.44
    Activations Density 0.001%

    No Known Activations