© 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. 29-GEMMASCOPE-2-RES-262K
    7. 146631
    Prev
    Next
    INDEX
    Explanations

    common assumptions

    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_29_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
     كس
    0.75
     forms
    0.71
    γραμμα
    0.67
     Faces
    0.65
     夕
    0.65
     resolved
    0.64
     ļ
    0.64
    ኔ
    0.64
    পিং
    0.63
    лга
    0.63
    POSITIVE LOGITS
     cư
    0.83
    ("#
    0.83
    ("",
    0.75
     керами
    0.75
     vijf
    0.73
    Theory
    0.72
    FIVE
    0.72
     transformada
    0.72
     cinq
    0.71
    NotIn
    0.71
    Activations Density 0.000%

    No Known Activations