© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 148679
    Prev
    Next
    INDEX
    Explanations

    pure social memes cut transport

    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
    났
    0.72
    ings
    0.72
    trend
    0.69
    assed
    0.67
    ibly
    0.65
    ored
    0.64
    пределение
    0.63
    ⠉
    0.63
    NELL
    0.62
    IRED
    0.61
    POSITIVE LOGITS
    e
    2.68
    es
    2.09
    E
    1.71
    ة
    1.59
    ee
    1.58
    eV
    1.52
    е
    1.51
    é
    1.42
     e
    1.41
    eb
    1.40
    Activations Density 0.026%

    No Known Activations