© 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. 13517
    Prev
    Next
    INDEX
    Explanations

    most, majority, some, certain

    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
     unenforceable
    0.40
     familiar
    0.39
    familiar
    0.39
    かを
    0.39
     understandably
    0.38
    კო
    0.38
    𝒌
    0.38
    茏
    0.38
    会员
    0.36
    മാനം
    0.36
    POSITIVE LOGITS
     plupart
    0.60
     большинства
    0.60
     niektórych
    0.59
     większość
    0.56
     большинство
    0.55
     vissa
    0.55
     версии
    0.54
     большинстве
    0.52
     certaines
    0.52
     பெரும்பாலான
    0.52
    Activations Density 0.206%

    No Known Activations