© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 86370
    Prev
    Next
    INDEX
    Explanations

    cannot take, many details, not disclose

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

    Rawlings, parenthesis, Violence

    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_31_width_262k_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
     in
    0.54
     Andrea
    0.49
     Cal
    0.49
     Kit
    0.49
     contention
    0.49
     Buffet
    0.47
     サ
    0.47
     liberation
    0.47
     Aberdeen
    0.46
     pensions
    0.46
    POSITIVE LOGITS
     таке
    0.55
    лись
    0.49
    ैक्ट
    0.46
    ائط
    0.45
    
    0.45
    ಂತ್ರ
    0.45
    ان
    0.44
     издания
    0.44
    ళ్ల
    0.44
     विक्रे
    0.43
    Activations Density 0.001%

    No Known Activations