© 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-262K
    7. 10903
    Prev
    Next
    INDEX
    Explanations

    Pandas Series and funding rounds

    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_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
    kaç
    1.92
    تی
    1.84
    
    1.73
    mselves
    1.69
    য়
    1.67
     reprogram
    1.66
    र्स
    1.63
     overruled
    1.61
    酶
    1.61
    ımın
    1.59
    POSITIVE LOGITS
    𝑔
    2.41
    ر
    2.36
    ти
    2.34
    р
    2.30
     locomotion
    2.01
    ר
    2.00
    nier
    1.93
    ycling
    1.88
     exponentes
    1.87
    ія
    1.85
    Activations Density 0.044%

    No Known Activations