© 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-65K
    4. 20147
    Prev
    Next
    INDEX
    Explanations

    concise rephrasing options

    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
     boda
    0.54
    ")}
    0.47
    ه‌های
    0.46
     война
    0.46
     Cochin
    0.46
    texto
    0.46
     siya
    0.46
     humiliating
    0.46
    ")]
    0.45
     Comanche
    0.45
    POSITIVE LOGITS
    气
    0.46
    Broadcast
    0.45
    主
    0.45
    车
    0.44
    ute
    0.44
    细
    0.44
    不太
    0.43
     bő
    0.42
    季
    0.42
    注
    0.41
    Activations Density 0.011%

    No Known Activations