© 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. 14309
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

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

    FP, SHA, IP, DDR, Series, d, H

    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
    aundice
    0.40
     Beschreibung
    0.40
    avoir
    0.39
    荥
    0.39
     मजा
    0.39
     Aguilera
    0.39
    zeczy
    0.38
     Johansson
    0.38
     Malhotra
    0.38
    傃
    0.38
    POSITIVE LOGITS
    １
    0.61
    1
    0.55
    ‐
    0.45
    Ⅰ
    0.43
    ３
    0.43
    -
    0.42
    XIV
    0.42
    3
    0.40
    ２
    0.40
    ０
    0.40
    Activations Density 0.132%

    No Known Activations