© 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. 10687
    Prev
    Next
    INDEX
    Explanations

    explosions

    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
     aflat
    2.80
    ан
    2.78
    et
    2.78
    $(".
    2.77
    crystalline
    2.56
    াল
    2.53
    agamo
    2.50
    etan
    2.47
     metade
    2.47
     legjob
    2.45
    POSITIVE LOGITS
    ী
    2.76
     mirando
    2.53
     그런데
    2.50
    eric
    2.49
    ்ட
    2.45
    ʹ
    2.36
    ere
    2.35
    え
    2.29
    場合に
    2.26
    n
    2.19
    Activations Density 0.007%

    No Known Activations