© 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. 91665
    Prev
    Next
    INDEX
    Explanations

    the word thereafter

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

    common prepositions and names

    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
     artık
    0.46
     stessi
    0.46
     ocurrió
    0.45
    ⓵
    0.43
    كيت
    0.43
    𐰇
    0.42
     গ্যাস
    0.42
    ታ
    0.42
     Aí
    0.41
     冖
    0.41
    POSITIVE LOGITS
     दश
    0.54
    ربی
    0.50
    ay
    0.45
     amenities
    0.45
    financing
    0.44
    ళ
    0.44
    ర్భ
    0.43
     оцен
    0.43
    dling
    0.42
     adjournment
    0.42
    Activations Density 0.001%

    No Known Activations