© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2148
    Prev
    Next
    INDEX
    Explanations

    legal topics and contexts

    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_9_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
    س
    3.41
    ان
    3.22
    ir
    3.11
    ˡ
    3.06
    وما
    3.02
    ل
    3.01
    ن
    2.99
     LoginComponent
    2.96
    śmy
    2.81
    g
    2.73
    POSITIVE LOGITS
     sebagainya
    2.93
    naire
    2.90
    andowski
    2.81
    써
    2.80
    naires
    2.73
    ться
    2.70
    ább
    2.69
    भग
    2.61
     fatto
    2.60
     insurg
    2.59
    Activations Density 0.423%

    No Known Activations