© 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. 222968
    Prev
    Next
    INDEX
    Explanations

    conversations with audiences, requests, new jobs, environmental topics

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

    specifically when

    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
    icionados
    0.55
    QUES
    0.50
    ｩ
    0.49
    솎
    0.49
    زاب
    0.49
    strel
    0.49
    irne
    0.48
    >[]
    0.48
    ンド
    0.47
     قومی
    0.47
    POSITIVE LOGITS
     Fuel
    0.57
     Derek
    0.56
     General
    0.55
     IF
    0.55
     Flask
    0.54
     ehrlich
    0.54
     Gö
    0.53
     Cover
    0.52
     Général
    0.52
     Guest
    0.52
    Activations Density 0.000%

    No Known Activations