© 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. 38713
    Prev
    Next
    INDEX
    Explanations

    underlying concepts

    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
     Bleu
    0.50
     Insert
    0.46
    $
    0.46
     Rd
    0.44
     ലെ
    0.43
     Tyl
    0.42
     sljede
    0.42
     Audio
    0.42
    codes
    0.42
     May
    0.41
    POSITIVE LOGITS
    логии
    0.52
    ющей
    0.48
    डून
    0.47
    ธุรก
    0.46
    ivo
    0.46
     پزشکی
    0.46
    слов
    0.45
    пи
    0.45
    眥
    0.45
    दर्द
    0.44
    Activations Density 0.000%

    No Known Activations