© 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-262K
    7. 34999
    Prev
    Next
    INDEX
    Explanations

    offering an alternative

    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
    -
    0.48
    Maxim
    0.43
    T
    0.41
    ou
    0.41
    الة
    0.40
    C
    0.40
    Leon
    0.40
    、
    0.40
    USS
    0.39
    Token
    0.39
    POSITIVE LOGITS
     phoned
    0.54
     පිළ
    0.50
     Eucalyptus
    0.49
     TextView
    0.48
     Breakfast
    0.48
     colorido
    0.48
     Mushrooms
    0.48
     Emerg
    0.47
     Fuels
    0.47
     Viruses
    0.47
    Activations Density 0.003%

    No Known Activations