© 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. 114386
    Prev
    Next
    INDEX
    Explanations

    when you or early planning

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

    temporal prerequisite or interval

    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
    方
    0.56
    說
    0.50
    3
    0.48
    兩
    0.47
     Qualquer
    0.46
    ா
    0.46
     papier
    0.45
    㓡
    0.44
     przy
    0.44
     方
    0.44
    POSITIVE LOGITS
     wilderness
    0.48
    IRIS
    0.47
    ꞌ
    0.47
     आईएफ
    0.46
     mezzanine
    0.45
    ﻙ
    0.45
    ushka
    0.44
    hattim
    0.44
     хотел
    0.43
     न्यूयॉर्क
    0.43
    Activations Density 0.000%

    No Known Activations