© 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. 130647
    Prev
    Next
    INDEX
    Explanations

    talk on winning details

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

    automation

    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
     gale
    0.48
     naw
    0.45
    거나
    0.42
     larga
    0.42
     ayrıca
    0.41
    niejszych
    0.41
    本社
    0.41
    ,$
    0.40
     dwóch
    0.40
    ＊
    0.40
    POSITIVE LOGITS
    Deps
    0.54
    NewUrl
    0.50
     Detecting
    0.49
    Webhook
    0.47
     পুরাতন
    0.47
    FAC
    0.47
     ставкалары
    0.47
     уены
    0.46
     ఆధ్యా
    0.46
    lyPlugin
    0.45
    Activations Density 0.001%

    No Known Activations