© 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. 49592
    Prev
    Next
    INDEX
    Explanations

    purification and extraction procedures

    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
    t
    0.77
    ר
    0.77
    to
    0.76
    r
    0.73
    d
    0.72
    ।
    0.72
    the
    0.70
    -
    0.70
    ’
    0.70
    LA
    0.69
    POSITIVE LOGITS
     ruim
    0.66
     devemos
    0.63
    iziModal
    0.62
     tradición
    0.61
     două
    0.59
     crucifix
    0.58
     Illumina
    0.58
     scap
    0.57
     evanescent
    0.57
     când
    0.57
    Activations Density 0.002%

    No Known Activations