© 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. 144741
    Prev
    Next
    INDEX
    Explanations

    specific terms and categories

    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
    has
    0.48
    久
    0.47
    dDevice
    0.45
    throwing
    0.44
    computation
    0.43
    y
    0.43
    過的
    0.43
    س
    0.42
    hi
    0.41
    )",
    0.41
    POSITIVE LOGITS
     unilateral
    0.65
     ridiculous
    0.60
     cheque
    0.56
     Christendom
    0.56
     stip
    0.55
     regl
    0.54
     wrongful
    0.54
     venda
    0.54
     stvar
    0.54
     unethical
    0.53
    Activations Density 0.000%

    No Known Activations