© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16765
    Prev
    Next
    INDEX
    Explanations

    numer or number followed by one

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

    systems, movement, numerology

    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
    틋
    0.40
    cèle
    0.40
    नाइटेड
    0.39
    Examin
    0.38
    erapeut
    0.38
    Edge
    0.38
    ეკ
    0.38
    leaning
    0.38
    Celula
    0.38
    素敵な
    0.38
    POSITIVE LOGITS
     विषय
    0.43
    ებისა
    0.42
     McCall
    0.42
    িক্যাল
    0.41
    唿
    0.41
    琀
    0.41
     Assassin
    0.40
     Tail
    0.40
    ivanja
    0.40
    otechnical
    0.40
    Activations Density 0.000%

    No Known Activations