© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174745
    Prev
    Next
    INDEX
    Explanations

    Zevon, Jay Z, Ally

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

    mental shortcuts, ways of thinking, proxy, questions

    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
    ুল
    0.50
    сион
    0.48
    Arithmetic
    0.48
    Thickness
    0.47
    ￠
    0.46
     Symmetric
    0.45
    وام
    0.45
    Uninstall
    0.44
    льнай
    0.44
    Foldout
    0.44
    POSITIVE LOGITS
     Sainsbury
    0.45
    瓤
    0.45
     acerc
    0.42
    ceme
    0.42
    itabbam
    0.42
     menyer
    0.41
     ময়
    0.41
     opportunità
    0.41
     разо
    0.40
     serp
    0.40
    Activations Density 0.001%

    No Known Activations