© 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. 41710
    Prev
    Next
    INDEX
    Explanations

    expert writer

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

    420 wjc gelatin middleware building Imports

    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
    IU
    0.61
    h
    0.52
    IA
    0.52
    cong
    0.51
    HAS
    0.50
    IH
    0.50
    IT
    0.50
     netted
    0.49
    opened
    0.49
    cP
    0.49
    POSITIVE LOGITS
    เพื่อ
    0.48
     guise
    0.45
    .
    0.45
     разум
    0.44
    使い
    0.44
     ताकि
    0.44
     cartridge
    0.44
     anthropological
    0.44
    それぞれの
    0.43
     garb
    0.43
    Activations Density 0.000%

    No Known Activations