© 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. 248642
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    Fus
    0.41
    枋
    0.40
    Attenuation
    0.38
     väč
    0.38
    ગી
    0.37
    ленную
    0.37
    澍
    0.36
     qDebug
    0.36
     می‌توان
    0.35
    әү
    0.35
    POSITIVE LOGITS
     poorly
    0.39
    projectName
    0.38
    los
    0.38
    chev
    0.37
     slog
    0.36
     constructor
    0.36
     unfinished
    0.36
    ++]
    0.36
    นะนำ
    0.35
     introductory
    0.35
    Activations Density 0.001%

    No Known Activations