© 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. 10835
    Prev
    Next
    INDEX
    Explanations

    feeling states

    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
    ার
    3.14
    𝑝
    3.09
    sail
    2.86
    ى
    2.76
    𝑒
    2.73
    multicolumn
    2.71
    𝑏
    2.68
    𝑜
    2.62
    我覺得
    2.61
     σημ
    2.61
    POSITIVE LOGITS
     compelled
    2.93
     nevoia
    2.63
     sorry
    2.60
    ület
    2.58
     logro
    2.52
     उसमे
    2.51
    mainwindow
    2.49
     religioso
    2.44
     меры
    2.43
     vontade
    2.38
    Activations Density 0.265%

    No Known Activations