© 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. 136818
    Prev
    Next
    INDEX
    Explanations

    response teams

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

    mentions of cryptocurrency

    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
    न्ड
    0.49
    ହ
    0.48
     resTmp
    0.48
    ENSOR
    0.47
     बढ़ाने
    0.46
     Qxa
    0.46
    MEDIUM
    0.46
    ULATORY
    0.46
    GREAT
    0.46
    INGO
    0.46
    POSITIVE LOGITS
    şi
    0.48
     stom
    0.48
    层
    0.47
    seys
    0.47
    ils
    0.44
    vel
    0.44
    ille
    0.43
    ás
    0.43
    sey
    0.43
    abil
    0.42
    Activations Density 0.000%

    No Known Activations