© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    lists prefixes and common English/Spanish words

    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
    ключение
    0.27
    сь
    0.26
    логии
    0.25
    ності
    0.25
    🠀
    0.25
    ለሁ
    0.25
     mesma
    0.25
     camaraderie
    0.25
    લું
    0.24
    ся
    0.24
    POSITIVE LOGITS
     
    0.41
     t
    0.27
     Ad
    0.26
     terakhir
    0.26
    ।
    0.25
     trei
    0.24
     Carousel
    0.24
    encil
    0.24
     C
    0.23
     drie
    0.22
    Activations Density 0.240%

    No Known Activations