© 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. 123399
    Prev
    Next
    INDEX
    Explanations

    human expertise

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

    tools, libraries, or scheduler purpose

    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
     সহিত
    0.46
    іга
    0.45
     documents
    0.43
    ilor
    0.43
     sequencing
    0.42
    ы
    0.42
     spectrum
    0.42
    ές
    0.42
    )،
    0.42
     library
    0.41
    POSITIVE LOGITS
    v
    0.49
    🥉
    0.49
    Prol
    0.49
    Limitations
    0.49
     Aussage
    0.48
    REAL
    0.47
     Durch
    0.46
    Normalize
    0.46
    ACH
    0.46
     darauf
    0.46
    Activations Density 0.001%

    No Known Activations