© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 18771
    Prev
    Next
    INDEX
    Explanations

    LMS / Meta AI / Calculus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geï
    0.62
    ந்
    0.60
    必
    0.59
     Hav
    0.59
    <unused581>
    0.59
     balloon
    0.58
     existing
    0.57
     Par
    0.57
     kah
    0.57
     vd
    0.57
    POSITIVE LOGITS
     LCA
    0.98
    Lb
    0.96
     LQ
    0.96
    MLL
    0.92
     LMF
    0.92
     LS
    0.92
     LH
    0.91
    🇱
    0.91
     LM
    0.90
    Lk
    0.90
    Activations Density 0.238%

    No Known Activations