© 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. 134938
    Prev
    Next
    INDEX
    Explanations

    | description |

    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
    اقات
    0.48
    ائرة
    0.47
    ingles
    0.46
    льны
    0.46
     ँ
    0.45
    ेंग
    0.45
     CHARSET
    0.44
    ರ್
    0.43
    ACTIONS
    0.42
    рованы
    0.41
    POSITIVE LOGITS
    那种
    0.53
    ນ
    0.53
     shot
    0.48
     pic
    0.48
     gdy
    0.48
    コン
    0.47
     wali
    0.47
     Javier
    0.46
    そういう
    0.46
     Ann
    0.46
    Activations Density 0.000%

    No Known Activations