© 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. 1191
    Prev
    Next
    INDEX
    Explanations

    work with / towards / around

    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
    м
    3.07
    ل
    3.02
    ु
    2.78
    ammam
    2.74
    其
    2.73
    ities
    2.71
     asunto
    2.69
    ו
    2.69
    可以
    2.68
    ്
    2.66
    POSITIVE LOGITS
    ेच्छा
    3.26
     tirelessly
    3.17
    ności
    2.95
    arounds
    2.92
    statt
    2.78
    manship
    2.54
    даги
    2.54
    bnb
    2.48
    да
    2.48
    
    2.46
    Activations Density 0.349%

    No Known Activations