© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    descriptive attributes followed by context

    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
    Getenv
    0.45
    Г
    0.43
    𝗠
    0.43
    CEEDINGS
    0.42
    𝗚
    0.41
    terrorism
    0.40
     теми
    0.39
    ން
    0.39
    Meet
    0.39
    ಡಿಯ
    0.38
    POSITIVE LOGITS
     seme
    0.40
     generously
    0.40
     Cualquier
    0.39
     parabolic
    0.38
     ""
    0.37
     sealing
    0.36
     uten
    0.36
     //!
    0.36
     với
    0.36
     guar
    0.36
    Activations Density 0.002%

    No Known Activations