© 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. 183705
    Prev
    Next
    INDEX
    Explanations

    service department. First timereasoned thatexciting light

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

    clusters

    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
     lèvres
    0.48
     নিঃসন্দেহে
    0.48
    ℏ
    0.46
    蓼
    0.45
    Buenas
    0.45
    коло
    0.45
     शब्दों
    0.45
     interstitiis
    0.43
    ਨ੍ਹਾਂ
    0.43
    Nau
    0.43
    POSITIVE LOGITS
     ս
    0.46
     ט
    0.46
     !=
    0.45
     ס
    0.44
    tin
    0.44
     stron
    0.44
     அளவுக்கு
    0.43
     ->
    0.43
     Servlet
    0.43
     〢
    0.43
    Activations Density 0.006%

    No Known Activations