© 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. 237597
    Prev
    Next
    INDEX
    Explanations

    patterns following 'you' and 'to'

    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
    ة
    0.48
     disposizione
    0.45
     ریاست
    0.43
     Trenton
    0.43
     کشتی
    0.42
    蜗
    0.42
     مقامی
    0.41
     States
    0.41
    discuss
    0.41
    =/
    0.41
    POSITIVE LOGITS
     isometric
    0.48
    хин
    0.45
    ྔ
    0.44
    ్యాచ్
    0.44
     améliorer
    0.43
     erhöhen
    0.43
     alcanza
    0.43
     стоимо
    0.42
     alveolar
    0.42
     pneumoniae
    0.42
    Activations Density 0.001%

    No Known Activations