© 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. 58608
    Prev
    Next
    INDEX
    Explanations

    phrases and connecting words

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

    shop listings, vendor details, patient info, endpoint agents

    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
    ListOf
    0.50
    在北京
    0.47
     도와
    0.47
     foil
    0.45
    Framework
    0.44
     foils
    0.43
     অপেক্ষায়
    0.43
    霍
    0.43
     تساعد
    0.43
     Affleck
    0.42
    POSITIVE LOGITS
    a
    0.54
     они
    0.51
    ą
    0.49
    itano
    0.49
    ä
    0.48
    nation
    0.47
    見た
    0.46
     വല
    0.46
     زیب
    0.46
     значения
    0.46
    Activations Density 0.000%

    No Known Activations