© 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. 16802
    Prev
    Next
    INDEX
    Explanations

    number followed by object

    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
    ad
    0.66
    the
    0.65
    c
    0.63
     போன்ற
    0.57
    The
    0.55
     the
    0.54
    ol
    0.53
    ap
    0.52
     River
    0.52
    disable
    0.52
    POSITIVE LOGITS
     tämä
    0.52
    0.51
    ’
    0.51
     monomers
    0.51
     delimiters
    0.51
     hallmarks
    0.50
    ering
    0.50
    0
    0.50
     omkring
    0.49
     Vereinigten
    0.49
    Activations Density 0.037%

    No Known Activations