© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147880
    Prev
    Next
    INDEX
    Explanations

    things you can taste

    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
     relatively
    0.80
     ridden
    0.80
     strapped
    0.80
    平安
    0.79
     hundreds
    0.78
     timelines
    0.78
     replete
    0.78
     ਫ
    0.77
     agencies
    0.76
     bà
    0.75
    POSITIVE LOGITS
    Riga
    0.78
    thesis
    0.77
     Raceway
    0.76
    SystemCall
    0.75
    పూర్
    0.75
    WeakTable
    0.75
    isotropic
    0.75
    ObjectTemp
    0.74
     circumstellar
    0.73
    antation
    0.73
    Activations Density 0.002%

    No Known Activations