© 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. 87794
    Prev
    Next
    INDEX
    Explanations

    heaven, put, go, certain, everytime, He

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

    specific technical terms and states

    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
     cordial
    0.50
    ков
    0.45
    abang
    0.45
    츠
    0.45
    кер
    0.45
    ্ক
    0.44
     relatable
    0.43
    ния
    0.43
     eigent
    0.43
     heartwarming
    0.43
    POSITIVE LOGITS
    rafpunkte
    0.53
    标准的
    0.46
    parseInt
    0.46
    没有人
    0.44
    STANDARD
    0.43
     사람들이
    0.43
     Synthetic
    0.43
    书籍
    0.43
    다
    0.43
     नाही
    0.42
    Activations Density 0.000%

    No Known Activations