© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84770
    Prev
    Next
    INDEX
    Explanations

    Paragu / supercavitating

    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
     atthakath
    0.56
    鸯
    0.54
    气息
    0.53
     Aś
    0.52
    atthakath
    0.51
     районе
    0.51
    ୍କ
    0.50
     personaje
    0.50
    结构的
    0.49
     Asalamualaikum
    0.48
    POSITIVE LOGITS
    0
    0.51
     "
    0.49
    «
    0.48
     reasoning
    0.45
    彼の
    0.45
     ->
    0.45
     a
    0.43
    rie
    0.43
     n
    0.43
     small
    0.42
    Activations Density 0.001%

    No Known Activations