© 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. 53094
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

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

    Viper launch, market better

    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
    deviceID
    0.59
    坭
    0.50
    chrono
    0.50
    তথ্য
    0.48
    чними
    0.48
    writeFile
    0.48
    TECHN
    0.46
    ي
    0.46
    bG
    0.46
    APPEND
    0.46
    POSITIVE LOGITS
     Team
    0.59
     Ring
    0.57
     Some
    0.56
     Day
    0.54
     Have
    0.52
     However
    0.51
     Market
    0.50
     stream
    0.49
     Here
    0.48
     Combat
    0.48
    Activations Density 0.000%

    No Known Activations