© 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. 184418
    Prev
    Next
    INDEX
    Explanations

    track audio, Envelope Case, men are, you think, blue account

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

    why certain things happen often

    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
     szkoły
    0.53
    ტი
    0.52
    有过
    0.50
     стаўкі
    0.49
    り
    0.46
     schedu
    0.44
     "?
    0.44
    汀
    0.44
     ティ
    0.43
     diálogo
    0.43
    POSITIVE LOGITS
    fst
    0.47
    ندس
    0.46
     AA
    0.44
     Comparable
    0.44
     Afro
    0.44
     SaaS
    0.44
     endl
    0.43
     Americas
    0.43
     PB
    0.43
     Pilots
    0.43
    Activations Density 0.001%

    No Known Activations