© 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. 123124
    Prev
    Next
    INDEX
    Explanations

    Never mind

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

    stiff neck

    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
    stå
    0.45
    rut
    0.45
     عادت
    0.44
    rukt
    0.44
    </h3>
    0.44
    olja
    0.43
     faç
    0.43
     اعتق
    0.43
    jenis
    0.42
    verk
    0.42
    POSITIVE LOGITS
    详解
    0.50
    引擎
    0.47
     দুর
    0.47
     arbres
    0.47
    垁
    0.46
    Beef
    0.45
    厙
    0.44
    鱼
    0.44
    鲑
    0.44
    悼
    0.43
    Activations Density 0.001%

    No Known Activations