© 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. 126729
    Prev
    Next
    INDEX
    Explanations

    4 Cylinder Engine

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

    technical and structured vocabulary

    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
    ссы
    0.51
    )，
    0.50
     OSU
    0.48
    成立
    0.45
    );
    0.45
    化
    0.45
    кої
    0.44
    かう
    0.44
    кими
    0.44
    )—
    0.44
    POSITIVE LOGITS
     berjumpa
    0.48
    ADER
    0.48
    produk
    0.48
    ס
    0.47
    ளோ
    0.47
     stoichiometric
    0.47
     fiz
    0.47
     रोक
    0.47
     produkt
    0.46
    ו
    0.44
    Activations Density 0.001%

    No Known Activations