© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    all of a set

    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
     ilang
    0.50
     ότι
    0.44
     niekoľ
    0.44
     နှင့်
    0.43
     nekaj
    0.43
     ottimo
    0.42
     ද
    0.41
     lezen
    0.41
     noite
    0.41
     několik
    0.41
    POSITIVE LOGITS
    (
    0.58
    نا
    0.50
     
    0.45
    Authenticated
    0.43
    Payload
    0.42
    Anal
    0.40
    Functional
    0.39
    Packaging
    0.39
    OfMonth
    0.39
    Adventure
    0.39
    Activations Density 0.406%

    No Known Activations