© 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. 221787
    Prev
    Next
    INDEX
    Explanations

    origin and destination

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

    feel or expect

    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
    needed
    0.50
    dostęp
    0.47
    必要な
    0.46
    ਕ
    0.46
    區
    0.46
     necessary
    0.45
     सेगमेंट
    0.45
    걔
    0.45
     مسیر
    0.44
     رہے۔
    0.44
    POSITIVE LOGITS
     algebraica
    0.51
     zes
    0.47
     alba
    0.47
     pengertian
    0.47
     pronoun
    0.46
     jazdy
    0.44
     bxa
    0.43
     í
    0.43
    Wing
    0.43
     is
    0.43
    Activations Density 0.000%

    No Known Activations