© 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. 16-GEMMASCOPE-2-RES-262K
    4. 1500
    Prev
    Next
    INDEX
    Explanations

    at followed by location/entity

    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
     of
    0.45
    ি
    0.40
    很
    0.36
    en
    0.35
    ",
    0.34
     de
    0.34
     nemen
    0.34
     in
    0.33
    as
    0.33
    וק
    0.33
    POSITIVE LOGITS
     چهار
    0.40
    t
    0.39
     Idaho
    0.36
     Bolton
    0.36
    k
    0.36
     Charlottesville
    0.35
     Astoria
    0.35
     Barbados
    0.35
     पांच
    0.34
     этот
    0.34
    Activations Density 0.227%

    No Known Activations