© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    significant portion

    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
     A
    0.51
     Effective
    0.50
    S
    0.50
    Whenever
    0.49
    *
    0.49
    Emma
    0.48
     Cana
    0.48
    ด
    0.48
     In
    0.47
     W
    0.47
    POSITIVE LOGITS
    τυχ
    0.56
     قيم
    0.55
    ᱒
    0.55
    قيم
    0.53
    pekte
    0.52
    لاسه
    0.52
    δα
    0.49
    浱
    0.49
    ισμό
    0.49
    letzt
    0.48
    Activations Density 0.000%

    No Known Activations