© 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. 44387
    Prev
    Next
    INDEX
    Explanations

    hardware and instructions

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

    name followed by punctuation

    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
     በር
    0.45
     успі
    0.41
     geweest
    0.41
     PW
    0.40
     reconfiguration
    0.40
    Д
    0.40
    ̇
    0.40
     ಬಂದ
    0.39
    П
    0.39
     ракет
    0.39
    POSITIVE LOGITS
     cột
    0.45
    াকৃত
    0.42
    隐藏
    0.40
    wire
    0.40
     মাঠ
    0.39
    Scopes
    0.39
    ilmesi
    0.38
     Chou
    0.38
    Wire
    0.38
     côté
    0.36
    Activations Density 0.001%

    No Known Activations