© 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. 16196
    Prev
    Next
    INDEX
    Explanations

    gram, grammar, or gram-negative

    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
    ל
    1.10
    ע
    1.05
    ك
    1.04
    та
    1.03
    ক
    0.96
    ために
    0.88
     a
    0.88
    ین
    0.88
    ם
    0.88
    ᴇ
    0.87
    POSITIVE LOGITS
    。
    0.92
     as
    0.91
    '
    0.89
    "
    0.86
    gram
    0.75
     Gram
    0.74
     Gramm
    0.73
     bör
    0.72
    න්ධ
    0.72
    r
    0.71
    Activations Density 0.004%

    No Known Activations