© 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. 73880
    Prev
    Next
    INDEX
    Explanations

    percentage discounts

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

    authorization code flow

    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
    azz
    0.44
    วัง
    0.42
    ../
    0.42
    ༔
    0.41
    avu
    0.41
    aug
    0.41
    एँ
    0.41
    트를
    0.40
    트
    0.40
    牍
    0.40
    POSITIVE LOGITS
     separable
    0.51
     jednom
    0.49
     રાશિફળ
    0.47
     pyrite
    0.47
     Cartan
    0.46
     danno
    0.46
     colloid
    0.46
     小型
    0.45
     transmittance
    0.45
     Brownian
    0.45
    Activations Density 0.001%

    No Known Activations