© 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. 83701
    Prev
    Next
    INDEX
    Explanations

    initiating actions or identifying entities

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

    price ranges

    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
    a
    0.52
     withdrew
    0.50
     Vietnam
    0.47
     følgende
    0.47
     informally
    0.45
     unsurprisingly
    0.45
     folgenden
    0.45
     mirroring
    0.44
     a
    0.44
     integra
    0.44
    POSITIVE LOGITS
    یاء
    0.55
    பாத
    0.51
    ዢ
    0.49
    晖
    0.48
     لگ
    0.47
    פה
    0.47
    uée
    0.47
    Entries
    0.45
     جیک
    0.44
    ंभ
    0.44
    Activations Density 0.000%

    No Known Activations