© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6945
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    喎
    0.85
    Ҳ
    0.84
    Bola
    0.82
    שה
    0.80
    Jwt
    0.80
    ॉरिटी
    0.79
     ſh
    0.78
    Kamu
    0.78
     keluar
    0.77
    푦
    0.77
    POSITIVE LOGITS
     strawberry
    0.73
     Nascimento
    0.72
     vanes
    0.72
     Vereins
    0.70
     vane
    0.70
     caballero
    0.70
     antecedentes
    0.68
    িত্ব
    0.67
    торое
    0.66
     perdido
    0.65
    Activations Density 0.000%

    No Known Activations