© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    specific noun phrase completions

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

    compound noun phrases

    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
    。",
    0.48
     startet
    0.44
    。
    0.43
    瑉
    0.42
    辏
    0.42
     costituito
    0.40
    াহীন
    0.40
    颧
    0.39
    ீரல்
    0.39
    পৃথ
    0.39
    POSITIVE LOGITS
    1
    0.53
    and
    0.47
    o
    0.46
     Emeritus
    0.45
     and
    0.45
    ِ
    0.43
    <b>
    0.42
    ik
    0.42
    ing
    0.42
    <0xEF>
    0.41
    Activations Density 1.117%

    No Known Activations