© 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. 66328
    Prev
    Next
    INDEX
    Explanations

    considering how to examine

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

    check or read

    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
    !</
    0.45
    थम
    0.44
    isième
    0.43
    न्ट
    0.42
     certamente
    0.42
     trazendo
    0.42
    elift
    0.41
     rispar
    0.41
    ﱢ
    0.40
    TTY
    0.40
    POSITIVE LOGITS
     bushes
    0.41
     aw
    0.41
     its
    0.38
    যুক্ত
    0.37
     typology
    0.37
    шло
    0.37
     nobleman
    0.37
    ങ്ങളാണ്
    0.36
     วั
    0.36
     what
    0.36
    Activations Density 0.018%

    No Known Activations