© 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. 144015
    Prev
    Next
    INDEX
    Explanations

    the word awful

    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
     a
    1.48
    s
    1.47
    d
    1.38
    y
    1.09
     at
    1.07
     s
    1.03
    ine
    0.98
    g
    0.97
    al
    0.95
     in
    0.92
    POSITIVE LOGITS
    ي
    1.48
    м
    1.31
    ર
    1.01
    يل
    0.97
    ి
    0.97
    يان
    0.95
    ان
    0.93
    то
    0.91
    떤
    0.90
    ன்
    0.89
    Activations Density 0.001%

    No Known Activations