© 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. 6850
    Prev
    Next
    INDEX
    Explanations

    many, more, from, controlled

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

    non-English characters and symbols

    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
    桦
    0.48
    outcome
    0.47
     adren
    0.45
     dependen
    0.45
     oka
    0.44
    ellos
    0.43
     Андрей
    0.43
    aughton
    0.43
    푹
    0.43
    elekt
    0.42
    POSITIVE LOGITS
     σε
    0.47
    的可
    0.46
     পৃথক
    0.46
    瞩
    0.45
     γνω
    0.45
    房价
    0.44
     صلاحیت
    0.44
     вважа
    0.43
     référence
    0.43
     μετα
    0.43
    Activations Density 0.000%

    No Known Activations