© 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. 10721
    Prev
    Next
    INDEX
    Explanations

    hexadecimal formatting, X word prefixes

    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
    t
    3.37
     convolutions
    2.84
     emas
    2.80
    сті
    2.76
     erst
    2.71
    पिछले
    2.63
    Sexy
    2.58
    Lorsque
    2.56
    Mientras
    2.52
    AMENTO
    2.49
    POSITIVE LOGITS
    ytocin
    3.32
    ೇತ್ರ
    3.31
    ceed
    3.17
    avier
    2.99
    ㇂
    2.82
    cellent
    2.77
     supposing
    2.70
     gleaming
    2.70
    倣
    2.66
    →</
    2.63
    Activations Density 0.262%

    No Known Activations