© 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. 1589
    Prev
    Next
    INDEX
    Explanations

    ASCII art cats

    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
    انة
    1.03
    య
    1.02
    착
    1.02
     たり
    1.01
    된
    1.00
     solchen
    0.98
    ิ
    0.98
     والسلام
    0.96
     skulle
    0.96
     preco
    0.96
    POSITIVE LOGITS
     рыба
    1.46
    arettes
    1.42
     осуществ
    1.41
     sleepless
    1.35
    tes
    1.35
    ती
    1.34
    〝
    1.33
    akespeare
    1.32
    ﺘ
    1.31
    athione
    1.31
    Activations Density 0.002%

    No Known Activations