© 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. 7316
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and programming constructs

    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
    tsprec
    1.22
     độ
    1.19
    𝚛
    1.17
     കുടുംബ
    1.16
     بزرگ
    1.15
     જો
    1.13
    𝚋
    1.13
    űr
    1.13
    lcnaf
    1.12
     とする
    1.11
    POSITIVE LOGITS
    y
    1.07
    s
    1.03
    izable
    0.99
    acing
    0.93
    anlı
    0.92
    ch
    0.89
    Scaled
    0.88
     ab
    0.88
     bout
    0.87
     భాగంగా
    0.80
    Activations Density 0.001%

    No Known Activations