© 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. 117018
    Prev
    Next
    INDEX
    Explanations

    dynamic programming indices

    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
    1.55
     as
    1.00
     govern
    0.98
     qualify
    0.93
     eradicate
    0.93
     impede
    0.91
     protect
    0.89
     promote
    0.89
     broaden
    0.89
     conséquent
    0.89
    POSITIVE LOGITS
    ond
    0.96
    s
    0.87
    v
    0.86
    <0x0D>
    0.85
    ς
    0.84
    ot
    0.82
    This
    0.80
    stek
    0.79
    \
    0.77
    L
    0.77
    Activations Density 0.002%

    No Known Activations