© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140206
    Prev
    Next
    INDEX
    Explanations

    theoretical physics

    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
    си
    0.60
     encontrados
    0.59
    OLYBD
    0.58
     lesquelles
    0.55
     tetrahedron
    0.54
     libras
    0.54
    る
    0.54
     cuales
    0.53
    ﴿
    0.53
     actuaciones
    0.53
    POSITIVE LOGITS
    un
    0.72
    x
    0.71
    ha
    0.65
    de
    0.62
    be
    0.61
    ot
    0.61
    apai
    0.59
    ate
    0.59
    ne
    0.59
    na
    0.59
    Activations Density 0.002%

    No Known Activations