© 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. 143063
    Prev
    Next
    INDEX
    Explanations

    starting retail price

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

    permissions and restrictions

    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
     anticipating
    0.47
     thôn
    0.45
     cricketer
    0.44
     [:
    0.43
     exposing
    0.43
     ଦ
    0.43
     gearing
    0.42
    يون
    0.42
     …
    0.41
     nhiệt
    0.41
    POSITIVE LOGITS
    IOS
    0.57
    Alle
    0.51
    Pier
    0.50
     Convent
    0.50
    Alternatives
    0.50
    Under
    0.48
    Manual
    0.48
    UC
    0.48
    Ŝ
    0.48
    ISE
    0.47
    Activations Density 0.001%

    No Known Activations