© 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. 7056
    Prev
    Next
    INDEX
    Explanations

    check if prime

    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
    S
    0.45
     اجيب
    0.44
    杉
    0.44
    จัด
    0.42
    ⊗
    0.42
     D
    0.41
     x
    0.40
     !=
    0.39
     offset
    0.39
     DC
    0.39
    POSITIVE LOGITS
    marginBottom
    0.48
     videre
    0.47
    microseconds
    0.46
     Apocalypse
    0.45
    ي
    0.45
    વાનો
    0.45
    totime
    0.44
    独特的
    0.44
    写入
    0.43
    rotated
    0.43
    Activations Density 0.012%

    No Known Activations