© 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. 251233
    Prev
    Next
    INDEX
    Explanations

    we looked or saw

    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
    ประกาศ
    0.51
     yeast
    0.51
    鉐
    0.49
     bromine
    0.47
     결혼
    0.47
    getRow
    0.47
     clickable
    0.46
     growers
    0.46
    আত্ম
    0.45
    acrylamide
    0.45
    POSITIVE LOGITS
    خير
    0.53
     Chees
    0.45
    ኋ
    0.43
     *}$
    0.41
    ën
    0.39
    Moody
    0.39
     Arten
    0.39
     Wex
    0.39
    AN
    0.38
    SUPPORT
    0.38
    Activations Density 0.000%

    No Known Activations