Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 1043
    Prev
    Next
    INDEX
    Explanations

    science, law, humanity

    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_16_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
    ai
    0.51
     e
    0.46
     are
    0.44
    cf
    0.41
    ?
    0.40
    kk
    0.40
    e
    0.40
     p
    0.39
    ا
    0.39
     intenso
    0.39
    POSITIVE LOGITS
    یاء
    0.37
     ignorance
    0.37
     dechlor
    0.37
     তাহাকে
    0.35
    ρυ
    0.34
     ridurre
    0.34
    ImageAsset
    0.34
    Denominator
    0.34
     distinguir
    0.33
     Moderne
    0.33
    Activations Density 0.355%

    No Known Activations