© 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. 201804
    Prev
    Next
    INDEX
    Explanations

    proverb that

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

    charge, agency, mass, electrons

    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
    老师
    0.50
    ↵↵↵
    0.49
    ↵↵
    0.47
    </blockquote>
    0.47
    شک
    0.46
     Ejemplo
    0.44
     customise
    0.44
     Controle
    0.43
     Multicolor
    0.43
    ↵↵↵↵↵↵
    0.42
    POSITIVE LOGITS
     afgelopen
    0.48
     ար
    0.45
     થો
    0.44
     состояния
    0.43
     ቦታ
    0.43
     journée
    0.42
     כמו
    0.42
     המו
    0.42
     clashes
    0.41
     mountainous
    0.41
    Activations Density 0.000%

    No Known Activations