© 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. 151861
    Prev
    Next
    INDEX
    Explanations

    leaders, work, red, available

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

    English, Abel, MongoDB

    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
     κι
    0.45
     casks
    0.45
     attacks
    0.44
    __'
    0.44
    clad
    0.44
     subunit
    0.43
     units
    0.42
     unity
    0.42
     clear
    0.42
     variations
    0.42
    POSITIVE LOGITS
    İ
    0.54
    افت
    0.51
    潍
    0.48
    宠
    0.47
    サービスの
    0.46
    ட்சி
    0.46
    żą
    0.46
     Komis
    0.45
    ة
    0.45
    ட்ச
    0.45
    Activations Density 0.000%

    No Known Activations