© 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. 109568
    Prev
    Next
    INDEX
    Explanations

    then and then

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

    correlation map

    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
    ives
    0.52
    ্ধু
    0.50
    אה
    0.46
    Ֆ
    0.45
    ్రె
    0.43
    โจ
    0.43
     filings
    0.43
    ään
    0.42
    ết
    0.42
    ტ
    0.42
    POSITIVE LOGITS
     kèm
    0.57
     المناطق
    0.50
    Dirs
    0.47
    OfDeath
    0.46
     là
    0.45
     باز
    0.45
     نماز
    0.44
     xảy
    0.44
     poes
    0.44
    就
    0.43
    Activations Density 0.000%

    No Known Activations