© 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. 198307
    Prev
    Next
    INDEX
    Explanations

    phrases describing a continuation

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

    introducing specific items or topics

    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
    찢
    0.50
    aments
    0.48
    知道
    0.45
    rutt
    0.44
    ad
    0.44
     industries
    0.44
    é
    0.43
    ы
    0.43
    。
    0.43
    打
    0.43
    POSITIVE LOGITS
     Nucleic
    0.49
     deja
    0.47
     İn
    0.46
     Choi
    0.45
     Chlorine
    0.45
     꼭
    0.45
    を含む
    0.44
     Streptococcus
    0.44
    '%(
    0.44
     Genome
    0.44
    Activations Density 0.000%

    No Known Activations