© 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. 236997
    Prev
    Next
    INDEX
    Explanations

    blog posts and questions

    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
    庥
    0.50
    秵
    0.49
    Parm
    0.49
    Atm
    0.47
    Marker
    0.47
     Chayin
    0.47
     إص
    0.47
    Celebrating
    0.47
    酵
    0.47
    荷兰
    0.46
    POSITIVE LOGITS
     pertinent
    0.47
     ➤
    0.46
     Viceroy
    0.44
     peacetime
    0.42
    word
    0.42
     eponym
    0.42
     stubbornly
    0.42
     taxonomic
    0.41
     electoral
    0.41
     behavioural
    0.41
    Activations Density 0.000%

    No Known Activations