© 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. 77750
    Prev
    Next
    INDEX
    Explanations

    bought up, feel better

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

    comparisons and lists of interests

    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
    ใน
    0.45
     hayat
    0.44
     vive
    0.44
     incumb
    0.43
     secondo
    0.43
     permette
    0.43
    泌
    0.42
     secund
    0.42
     profess
    0.42
     في
    0.41
    POSITIVE LOGITS
     पका
    0.45
    ванных
    0.45
     альбо
    0.44
    Ꮸ
    0.44
    masks
    0.43
     Gif
    0.43
    níků
    0.43
    ANGMAR
    0.43
     насла
    0.42
    britannien
    0.42
    Activations Density 0.000%

    No Known Activations