© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40091
    Prev
    Next
    INDEX
    Explanations

    A newly

    np_acts-logits-general · gemini-2.5-flash-lite

    reduced paperwork, costs, consumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    res
    0.54
    ar
    0.53
    en
    0.48
    le
    0.48
    R
    0.48
    built
    0.45
    re
    0.45
    urdy
    0.45
    ne
    0.45
    ous
    0.44
    POSITIVE LOGITS
    জিৎ
    0.47
     মিড
    0.45
    testAvg
    0.44
    dSample
    0.44
     interrogated
    0.44
    鲔
    0.44
     йил
    0.43
     বছ
    0.43
     மேலே
    0.43
     همچ
    0.43
    Activations Density 0.000%

    No Known Activations