© 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. 4793
    Prev
    Next
    INDEX
    Explanations

    Common word beginnings

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

    words following certain tokens

    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
     to
    0.30
    1
    0.24
     for
    0.21
    to
    0.20
     on
    0.19
    0
    0.19
     from
    0.18
    ليس
    0.18
    2
    0.17
     with
    0.17
    POSITIVE LOGITS
    的的
    0.20
    ഌ
    0.18
    ७
    0.18
    ナソニック
    0.18
     thre
    0.18
    ઁ
    0.17
    టువంటి
    0.17
     grotes
    0.17
    ीडियो
    0.17
     beak
    0.17
    Activations Density 4.525%

    No Known Activations