© 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. 161144
    Prev
    Next
    INDEX
    Explanations

    producer, author, last name

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

    mathematical and descriptive concepts

    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
     дошко
    0.51
     გამო
    0.49
    蛎
    0.48
     FOR
    0.47
     позна
    0.46
     ช่วง
    0.44
    หรือ
    0.43
     BUDGET
    0.43
     представи
    0.43
     वृद्धि
    0.43
    POSITIVE LOGITS
    馄
    0.49
    كلة
    0.46
    alibaba
    0.45
     খাওয়া
    0.44
    هلاك
    0.43
    comments
    0.42
    ্লোক
    0.41
     জগৎ
    0.41
    ﮔ
    0.41
    FileList
    0.41
    Activations Density 0.001%

    No Known Activations