© 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. 1352
    Prev
    Next
    INDEX
    Explanations

    requests for five similar tools

    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
    もちろん
    2.77
     Euler
    2.73
     ora
    2.70
    an
    2.61
    ї
    2.59
    मो
    2.53
    स
    2.48
     były
    2.46
     hires
    2.43
    에
    2.37
    POSITIVE LOGITS
    деся
    4.41
    десят
    3.89
     WENO
    3.18
     boroughs
    2.91
    ן
    2.82
    ю
    2.81
    hmC
    2.80
    ोरा
    2.77
    pyrazol
    2.76
    entially
    2.74
    Activations Density 0.274%

    No Known Activations