© 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. 62121
    Prev
    Next
    INDEX
    Explanations

    Guy Named

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

    devoured generations dinosaurs Kingdom verbose

    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
     hota
    0.38
     principales
    0.37
    প্রধান
    0.37
     ausgewählt
    0.37
     prohibitions
    0.37
     recovers
    0.36
    㑔
    0.36
    貽
    0.36
     frü
    0.36
     Bew
    0.36
    POSITIVE LOGITS
     малень
    0.52
     неболь
    0.48
     איך
    0.48
    马
    0.47
     буквально
    0.45
    ÇA
    0.44
    buscar
    0.43
    Это
    0.42
    ╩
    0.42
     это
    0.42
    Activations Density 0.000%

    No Known Activations