© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9881
    Prev
    Next
    INDEX
    Explanations

    so and sock words

    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_40_width_16k_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
    deki
    0.47
    df
    0.45
    decrease
    0.42
    del
    0.41
    ὕ
    0.41
    unn
    0.41
    in
    0.40
    ense
    0.40
     Restart
    0.40
    ΐ
    0.40
    POSITIVE LOGITS
     ソ
    0.75
     Со
    0.68
    Со
    0.65
     సో
    0.64
     সো
    0.61
     સો
    0.58
     सो
    0.58
     SO
    0.56
    索
    0.55
    ソ
    0.54
    Activations Density 0.099%

    No Known Activations