© 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-262K
    7. 2228
    Prev
    Next
    INDEX
    Explanations

    Registry connection

    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_262k_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
    archiw
    0.39
    ransform
    0.38
    zonego
    0.37
    eksiyon
    0.36
    akkhati
    0.35
    parvec
    0.35
    솎
    0.35
    묽
    0.35
    getStudentNo
    0.35
    apanicola
    0.35
    POSITIVE LOGITS
     G
    0.59
     _
    0.57
     R
    0.54
     r
    0.54
     p
    0.54
     C
    0.53
     T
    0.51
     M
    0.51
     B
    0.51
     c
    0.50
    Activations Density 0.056%

    No Known Activations