© 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. 219787
    Prev
    Next
    INDEX
    Explanations

    authority in market

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

    specific situation, fit, train

    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
     ajouter
    0.54
     它
    0.53
     Ajoutez
    0.53
     Voraus
    0.51
    zí
    0.50
     他们
    0.50
     清
    0.50
     ആദ്യം
    0.49
     au
    0.49
     首先
    0.48
    POSITIVE LOGITS
    कारों
    0.52
    ան
    0.48
    रि
    0.46
    रो
    0.44
    浄
    0.44
    ἀ
    0.44
    นิ
    0.43
    ंबर्स
    0.43
    懺
    0.43
    มะ
    0.43
    Activations Density 0.001%

    No Known Activations