© 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. 36066
    Prev
    Next
    INDEX
    Explanations

    preposition or article following

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

    advantages and disadvantages

    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
    ，
    0.47
     Alters
    0.44
     UND
    0.42
    files
    0.40
     comme
    0.40
    Inet
    0.39
    ங்க
    0.39
    Bonjour
    0.39
    Acetic
    0.39
    0
    0.39
    POSITIVE LOGITS
     quantità
    0.54
    ैटिन
    0.48
    ನಿಯ
    0.47
    spaceBetween
    0.47
     bury
    0.46
    హు
    0.46
    ಕೊ
    0.46
     силы
    0.45
     Möglich
    0.44
     istek
    0.44
    Activations Density 0.000%

    No Known Activations