© 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. 49507
    Prev
    Next
    INDEX
    Explanations

    following events or steps

    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
     که
    0.95
    områ
    0.92
    는
    0.85
    vě
    0.77
    vět
    0.77
     کہ
    0.76
    vär
    0.75
    は
    0.75
     کە
    0.74
    ows
    0.74
    POSITIVE LOGITS
     використання
    0.77
     использование
    0.71
     subsequent
    0.70
     videre
    0.66
    ल
    0.66
    鋐
    0.66
     shepherd
    0.66
     procesamiento
    0.66
     ricon
    0.65
     vape
    0.64
    Activations Density 0.003%

    No Known Activations