© 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. 83957
    Prev
    Next
    INDEX
    Explanations

    to say that

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

    to deny or lose

    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
     стаўкі
    0.50
     synagogues
    0.49
     bardziej
    0.48
    𝑨
    0.48
     všech
    0.46
    较大
    0.45
     episcopal
    0.45
    𒊺
    0.45
    𒄭
    0.44
    茶叶
    0.44
    POSITIVE LOGITS
    ia
    0.53
    om
    0.49
    og
    0.47
    the
    0.46
    st
    0.44
    tz
    0.44
    mo
    0.44
    ist
    0.43
    ine
    0.43
    je
    0.43
    Activations Density 0.006%

    No Known Activations