© 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. 34176
    Prev
    Next
    INDEX
    Explanations

    ammonia

    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
    o
    1.10
    p
    1.09
    in
    1.08
    am
    1.04
    ir
    1.02
    on
    0.91
    y
    0.90
    un
    0.89
    gra
    0.89
    etty
    0.87
    POSITIVE LOGITS
    3
    1.30
    ли
    1.24
    푞
    1.08
    ت
    1.07
    은
    1.06
    נ
    1.05
    ۶
    1.05
    С
    1.02
    は
    1.02
    5
    1.00
    Activations Density 0.002%

    No Known Activations