© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2948
    Prev
    Next
    INDEX
    Explanations

    numbers eighteen to twenty

    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_29_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
    ১২
    0.82
    ۱۲
    0.80
     १००
    0.75
     तुमच्या
    0.75
    १०
    0.73
    ✥
    0.72
     டா
    0.69
     πά
    0.69
     Poo
    0.67
    ১০
    0.67
    POSITIVE LOGITS
    ۲۰
    1.16
     nineteen
    1.10
     २०
    1.06
     ۲۰
    1.06
    २०
    1.02
     eighteen
    1.00
     XIX
    0.99
     ২০
    0.98
    十九
    0.98
     eighteenth
    0.95
    Activations Density 0.415%

    No Known Activations