© 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. 224445
    Prev
    Next
    INDEX
    Explanations

    shows Foxconn

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

    asking questions

    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
    cultures
    0.49
     mediators
    0.48
    scoreboard
    0.47
    bedo
    0.46
    纶
    0.46
    rails
    0.46
    buffers
    0.45
    templat
    0.44
    directories
    0.44
    duty
    0.44
    POSITIVE LOGITS
     DeS
    0.49
     Sou
    0.48
    Sou
    0.46
     a
    0.46
     mikro
    0.45
    閆
    0.45
     Kein
    0.44
     ショート
    0.44
    িকো
    0.44
     dieser
    0.43
    Activations Density 0.001%

    No Known Activations