© 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. 145723
    Prev
    Next
    INDEX
    Explanations

    festival parking

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

    inform, reveal, request, Relax

    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
    एल
    0.46
    悪い
    0.46
     legitimacy
    0.45
    아
    0.43
    ほか
    0.43
     exaggeration
    0.42
    贔
    0.42
    त्य
    0.42
    同じ
    0.41
    र्ता
    0.41
    POSITIVE LOGITS
     খুঁ
    0.50
     gins
    0.47
    ₚ
    0.46
     Fonbet
    0.46
    цион
    0.46
     ekspl
    0.45
    zinger
    0.44
     teori
    0.44
     forhold
    0.44
     Sachin
    0.44
    Activations Density 0.000%

    No Known Activations