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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 458
    Prev
    Next
    INDEX
    Explanations

    What kind of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     а
    0.60
     или
    0.57
    *
    0.56
    :
    0.54
     *
    0.53
    気軽に
    0.52
     or
    0.51
     любого
    0.49
    л
    0.48
     of
    0.47
    POSITIVE LOGITS
     volver
    0.82
    dataSet
    0.81
     viene
    0.80
     turut
    0.80
     dalje
    0.80
    цэ
    0.79
     możliwe
    0.79
    טורק
    0.79
     delen
    0.79
     farmland
    0.78
    Activations Density 0.005%

    No Known Activations