© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1225
    Prev
    Next
    INDEX
    Explanations

    as modern

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

    common connectors and modifiers

    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
    benzoimidazole
    0.42
     ষ্ট
    0.42
    栆
    0.41
    ণিক
    0.40
    の種類
    0.39
     deposito
    0.38
    텟
    0.38
     entrees
    0.38
    麴
    0.38
    することができる
    0.38
    POSITIVE LOGITS
    edm
    0.36
    </span>
    0.34
     }^{
    0.34
    <0x0D>
    0.33
    edu
    0.33
     ­
    0.33
     (
    0.33
    </i>
    0.33
    </b>
    0.33
    ن
    0.32
    Activations Density 0.115%

    No Known Activations