© 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. 149691
    Prev
    Next
    INDEX
    Explanations

    large bowl, low risk, never answer

    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
     satisfying
    0.68
    홧
    0.68
     satisfies
    0.67
     surprising
    0.66
     exactamente
    0.66
     masa
    0.65
    culo
    0.65
     transforms
    0.64
    วิว
    0.64
    icherweise
    0.64
    POSITIVE LOGITS
    Gur
    0.87
     Bomb
    0.79
    gur
    0.77
     चिकन
    0.76
    ZZ
    0.75
    鲢
    0.74
     प्रिंस
    0.72
     eğitimi
    0.72
     Gur
    0.72
    ène
    0.71
    Activations Density 0.003%

    No Known Activations