© 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. 190314
    Prev
    Next
    INDEX
    Explanations

    part, wan, car, dri, shal

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

    controlling or special information

    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
    i
    0.51
    터
    0.51
    at
    0.50
     Allocation
    0.50
     Episodes
    0.47
     Overview
    0.47
     Speaker
    0.46
     Location
    0.46
     Rule
    0.46
    Overview
    0.46
    POSITIVE LOGITS
     convivial
    0.46
     مطال
    0.45
    sekut
    0.45
    etric
    0.45
    delen
    0.45
    ቱ
    0.44
     ressources
    0.44
    覂
    0.43
     VW
    0.43
     institu
    0.43
    Activations Density 0.000%

    No Known Activations