© 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. 223639
    Prev
    Next
    INDEX
    Explanations

    details, rules, lists, order

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

    ranking lists about groups

    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
    Þ
    0.44
     on
    0.44
     naud
    0.44
    e
    0.43
    js
    0.43
     ligt
    0.43
     Lumi
    0.43
    east
    0.43
     icin
    0.42
    yst
    0.42
    POSITIVE LOGITS
     άλ
    0.55
    อัล
    0.51
    。”
    0.48
     શબ્
    0.48
     дове
    0.46
     йөкләү
    0.46
     млад
    0.45
     τότε
    0.45
    敨
    0.45
    𝒐
    0.44
    Activations Density 0.001%

    No Known Activations