© 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-65K
    7. 3919
    Prev
    Next
    INDEX
    Explanations

    code with models and parameters

    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_65k_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
    من
    0.49
    ه
    0.46
    ن
    0.43
    national
    0.42
    مد
    0.42
    عند
    0.42
     सरफेस
    0.42
    essential
    0.42
    функциона
    0.42
    REIB
    0.42
    POSITIVE LOGITS
     {}>,
    0.45
     A
    0.43
     Judge
    0.39
     qDebug
    0.38
     >
    0.38
     progressBar
    0.38
     Grant
    0.37
     elapsed
    0.37
     Fewer
    0.37
     `>=`,
    0.36
    Activations Density 0.251%

    No Known Activations