© 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. 130822
    Prev
    Next
    INDEX
    Explanations

    records, stakes, and numbers

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

    follow closely, oceans

    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
    ध्द
    0.55
     Eurostile
    0.45
    剱
    0.45
     ক্ষয়ক্ষতি
    0.45
    when
    0.44
    defined
    0.44
    俶
    0.43
     Discussions
    0.42
     loophole
    0.42
    Speech
    0.42
    POSITIVE LOGITS
    ás
    0.55
    rás
    0.49
     ás
    0.49
     опро
    0.46
    ính
    0.46
     marbled
    0.46
    át
    0.45
    <unused693>
    0.45
    çando
    0.45
    íses
    0.45
    Activations Density 0.002%

    No Known Activations