© 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. 75172
    Prev
    Next
    INDEX
    Explanations

    viagra

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

    learns about names and representations

    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
    oom
    0.48
     초
    0.47
    ﻈ
    0.47
    woman
    0.46
    ষা
    0.46
     entonces
    0.46
    ﻌ
    0.45
     logarithmic
    0.44
     jaaye
    0.44
    case
    0.43
    POSITIVE LOGITS
    TextColor
    0.43
     ہوئے۔
    0.42
    ៕
    0.42
     extérieures
    0.41
    メーター
    0.40
     ذریع
    0.40
    Tareas
    0.40
    Eternal
    0.39
    Athena
    0.39
     строительства
    0.39
    Activations Density 0.001%

    No Known Activations