© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6154
    Prev
    Next
    INDEX
    Explanations

    scripting and timing markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    ה
    1.07
    لا
    1.06
    𝒐
    1.03
    roidism
    0.97
    째
    0.94
    gir
    0.91
    nutrition
    0.91
    i
    0.90
    required
    0.90
    nature
    0.90
    POSITIVE LOGITS
     juxtap
    1.04
     condiv
    1.02
     rêves
    1.00
    ğmen
    0.99
     consonants
    0.97
     cassettes
    0.97
     namen
    0.95
     belong
    0.94
     lancio
    0.94
     paréntesis
    0.94
    Activations Density 0.012%

    No Known Activations