© 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. 13344
    Prev
    Next
    INDEX
    Explanations

    loan prediction and error messages

    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
    ________________
    1.03
    ه
    0.95
    બ
    0.91
    TECHN
    0.85
    িল
    0.83
    ----------------
    0.83
    ________
    0.82
    те
    0.80
    பட
    0.79
     what
    0.78
    POSITIVE LOGITS
     rss
    1.16
    hanti
    1.14
     chamb
    1.13
     vhod
    1.07
     grasa
    1.07
    躇
    1.04
    ahuje
    1.03
    งิน
    1.02
     daging
    1.01
     knapp
    0.99
    Activations Density 0.004%

    No Known Activations