© 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. 26720
    Prev
    Next
    INDEX
    Explanations

    who will visit or chat

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

    software, services, api

    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
     ஆகும்
    0.50
     식품
    0.48
     ~$
    0.46
    <unused42>
    0.45
     Plessis
    0.45
    🈺
    0.45
     후보
    0.45
    录取
    0.45
     János
    0.45
    வதில்லை
    0.44
    POSITIVE LOGITS
    Visit
    0.46
    opend
    0.46
    chat
    0.46
    Madrid
    0.43
    ंग
    0.42
    श
    0.42
    CHAT
    0.41
    噂
    0.41
    Chat
    0.41
     rumours
    0.41
    Activations Density 0.000%

    No Known Activations