© 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. 11086
    Prev
    Next
    INDEX
    Explanations

    losing weight or oneself

    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
    antiate
    2.65
    akel
    2.45
    unun
    2.41
     μέσω
    2.39
    weise
    2.37
    يون
    2.34
     Euclidean
    2.31
     亻
    2.27
    రించ
    2.27
    dataTable
    2.26
    POSITIVE LOGITS
    ти
    3.37
    inafter
    2.92
    こともある
    2.74
    ippy
    2.73
     angeles
    2.61
     metr
    2.60
    jangan
    2.59
    器
    2.56
     tendre
    2.51
    issippi
    2.50
    Activations Density 0.040%

    No Known Activations