© 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. 37067
    Prev
    Next
    INDEX
    Explanations

    numbers represents ASCII codes

    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
    )$,
    0.42
    ։
    0.42
     ਜਾਂ
    0.41
     судо
    0.40
    ബരിമല
    0.40
     supernatants
    0.40
     кома
    0.39
     проце
    0.38
    Ice
    0.38
    츠
    0.38
    POSITIVE LOGITS
     promesa
    0.52
     perceptive
    0.49
    يمان
    0.48
     React
    0.47
     layman
    0.47
     ricerca
    0.46
     wissen
    0.46
     topics
    0.46
     conocer
    0.46
    ก
    0.46
    Activations Density 0.002%

    No Known Activations