© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113107
    Prev
    Next
    INDEX
    Explanations

    Attention is All You Need

    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
    បន្ថែម
    0.48
    詡
    0.48
     Bericht
    0.46
    編
    0.45
    طقة
    0.45
     sektor
    0.45
     Textured
    0.44
    ಪಟ್ಟ
    0.44
    ㄎ
    0.43
     ګ
    0.43
    POSITIVE LOGITS
    LI
    0.47
    Research
    0.46
     descu
    0.44
    Time
    0.44
    MON
    0.43
     desconoc
    0.43
     deoarece
    0.43
    Campe
    0.42
    Mon
    0.42
    TER
    0.42
    Activations Density 0.003%

    No Known Activations