© 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. 111778
    Prev
    Next
    INDEX
    Explanations

    parts or units

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

    distances, Resin, Expectations, storage, wisdom, originally

    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
    abhavena
    0.49
     получили
    0.48
     заменить
    0.46
    angkan
    0.44
    }=(
    0.44
     представители
    0.43
     получила
    0.43
    悝
    0.42
    鸬
    0.41
    nač
    0.41
    POSITIVE LOGITS
     prossima
    0.52
     زیرمه
    0.45
     impoverished
    0.45
     biodegradation
    0.45
     nhưng
    0.44
    ل
    0.44
     sexy
    0.43
     restroom
    0.43
     expectations
    0.42
     travertine
    0.42
    Activations Density 0.000%

    No Known Activations