© 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. 16999
    Prev
    Next
    INDEX
    Explanations

    Personal engagement and positive feedback

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

    processes and actions

    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
    stern
    0.48
    Widget
    0.46
    egraphics
    0.45
     glassware
    0.45
     школи
    0.44
    кти
    0.43
     GREEN
    0.43
    모
    0.43
     структуры
    0.43
     вывести
    0.43
    POSITIVE LOGITS
     قام
    0.44
    瞇
    0.44
     उसकी
    0.42
    fica
    0.41
     několik
    0.41
    ঠিক
    0.40
     اُن
    0.40
     alloying
    0.40
     اخذت
    0.39
    ژی
    0.39
    Activations Density 0.000%

    No Known Activations