© 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. 145260
    Prev
    Next
    INDEX
    Explanations

    special features

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

    energy field

    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
     Industri
    0.49
    Bs
    0.47
    早速
    0.47
     Рассмотрим
    0.46
     blacks
    0.45
     Iz
    0.45
    Kuch
    0.45
    勍
    0.45
     Gradually
    0.45
     Muslims
    0.43
    POSITIVE LOGITS
     inextric
    0.43
    '_
    0.42
     наве
    0.42
    '.
    0.42
    ってる
    0.42
     navegar
    0.41
    닼
    0.41
     trouve
    0.41
    ına
    0.41
     عر
    0.41
    Activations Density 0.001%

    No Known Activations