© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 106837
    Prev
    Next
    INDEX
    Explanations

    long, round, or go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    -
    0.71
    _
    0.71
    n
    0.64
     فِي
    0.63
    ya
    0.63
    <0x89>
    0.61
    )
    0.61
    :
    0.60
    ad
    0.59
    }.
    0.59
    POSITIVE LOGITS
     antigo
    0.64
    은
    0.63
     telefone
    0.63
    ทำงาน
    0.59
     veja
    0.59
     bloke
    0.59
    the
    0.58
    जी
    0.58
    ไม่มี
    0.58
     rije
    0.57
    Activations Density 0.000%

    No Known Activations