© 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. 39233
    Prev
    Next
    INDEX
    Explanations

    describing changes and reasons

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

    answers, bike, vibe, elegant, for

    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
    c
    0.46
    或其他
    0.42
    移
    0.42
    meg
    0.41
     номина
    0.41
    ી
    0.41
    of
    0.41
    té
    0.41
    moved
    0.41
    ប្រទេស
    0.40
    POSITIVE LOGITS
     připoj
    0.49
     எரி
    0.49
     glows
    0.47
     ensures
    0.46
     കത്തി
    0.45
    Says
    0.45
     tires
    0.45
     całym
    0.43
     kısa
    0.43
     którym
    0.43
    Activations Density 0.000%

    No Known Activations