© 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. 155052
    Prev
    Next
    INDEX
    Explanations

    No matter what

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

    fast montage of

    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
    <unused1086>
    0.52
    StaticHandler
    0.50
     මෙම
    0.49
     forment
    0.49
     แถม
    0.49
     amelyek
    0.47
     Colonia
    0.47
    க்கவும்
    0.46
     അടിസ്ഥാന
    0.46
    |+\
    0.46
    POSITIVE LOGITS
    oi
    0.45
    Urs
    0.45
    .'%
    0.45
    SearchResults
    0.42
    string
    0.42
    जरी
    0.41
     string
    0.41
    incer
    0.40
    편
    0.40
    Ide
    0.40
    Activations Density 0.001%

    No Known Activations