© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3509
    Prev
    Next
    INDEX
    Explanations

    Hebrew text and names

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

    ://fortifyprogram.org

    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_53_width_65k_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
    호를
    0.42
    வி
    0.40
    존
    0.39
    دى
    0.37
     احترام
    0.37
    äume
    0.37
     revolutionary
    0.36
     उम्र
    0.35
     dihasil
    0.35
    ﺅ
    0.35
    POSITIVE LOGITS
    בודה
    0.69
    ניין
    0.68
    בוד
    0.57
    ליה
    0.55
    ליו
    0.50
    סק
    0.50
    קב
    0.50
    ולם
    0.49
    מוד
    0.47
    ץ
    0.43
    Activations Density 0.003%

    No Known Activations