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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 143580
    Prev
    Next
    INDEX
    Explanations

    Google Photos

    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
    ajal
    0.40
    ष
    0.40
     ریاست
    0.39
    三次
    0.39
     boli
    0.39
    ள்
    0.38
    ষ
    0.38
    jaer
    0.38
     covariant
    0.38
    銘
    0.38
    POSITIVE LOGITS
     possède
    0.46
     Nutzung
    0.46
     kullanımı
    0.46
     korzyst
    0.44
     verfügt
    0.44
     употреб
    0.44
     eBooks
    0.43
     повністю
    0.43
     qualités
    0.42
     Discord
    0.42
    Activations Density 0.011%

    No Known Activations