© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    review

    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
    ה
    4.78
    a
    3.81
    ʟ
    3.31
     proc
    3.28
    siniz
    2.98
    ن
    2.95
    en
    2.88
    े
    2.79
    ɴ
    2.77
    ા
    2.72
    POSITIVE LOGITS
    ల
    3.12
    rš
    2.99
    러
    2.97
    𝔀
    2.89
    vat
    2.81
    ー
    2.78
    شی
    2.78
    𝐢
    2.77
    ਲ
    2.76
     einzige
    2.75
    Activations Density 0.426%

    No Known Activations