© 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-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 99808
    Prev
    Next
    INDEX
    Explanations

    outcomes and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    闢
    0.48
     też
    0.48
    r
    0.46
    并且
    0.46
     ग्लास
    0.45
    𝙨
    0.45
     natomiast
    0.44
    🎧
    0.44
    larımız
    0.43
    riculum
    0.43
    POSITIVE LOGITS
     Vaill
    0.46
     diffusion
    0.42
    at
    0.41
     Gewinn
    0.40
    যোগে
    0.40
    Implement
    0.39
    ियोग
    0.39
     ٻ
    0.39
     harvest
    0.38
     deque
    0.38
    Activations Density 0.003%

    No Known Activations