© 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. 57491
    Prev
    Next
    INDEX
    Explanations

    on Air Hockey, your favorite, Your order

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

    habitual bias or minimal effort

    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
    ósfera
    0.47
     refraction
    0.46
    流畅
    0.46
     shimmer
    0.46
    cję
    0.46
     άν
    0.46
     వు
    0.46
    砖
    0.44
    ⼀
    0.44
    áno
    0.44
    POSITIVE LOGITS
    soon
    0.45
    Й
    0.43
    straight
    0.41
    nomina
    0.40
    Da
    0.39
    False
    0.39
     pouvaient
    0.39
    打算
    0.38
    اي
    0.38
    loving
    0.38
    Activations Density 0.000%

    No Known Activations