© 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. 7087
    Prev
    Next
    INDEX
    Explanations

    Certificate Transparency

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

    coding and multilingual text

    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
    //}
    0.50
     அது
    0.36
    ܘ
    0.35
    
    0.35
    /),
    0.35
     তাহার
    0.34
    Yet
    0.34
    ///
    0.34
     оно
    0.34
     catapult
    0.34
    POSITIVE LOGITS
    muz
    0.39
     নাইট
    0.38
    ﹌
    0.37
    ronomie
    0.36
    świet
    0.36
    ほどの
    0.36
     হিসেবে
    0.35
    ắm
    0.35
    褻
    0.35
    esten
    0.35
    Activations Density 0.000%

    No Known Activations