© 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. 137624
    Prev
    Next
    INDEX
    Explanations

    infrastructure and transportation

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

    ELK stack and infrastructure

    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
     Sản
    0.46
    getField
    0.46
    제품
    0.41
     Đặc
    0.41
     Informasi
    0.41
     ورلڈ
    0.40
    __)
    0.40
    ༢
    0.40
    जनबी
    0.40
    😉
    0.40
    POSITIVE LOGITS
     shackles
    0.48
    すぐに
    0.48
    penas
    0.46
    killing
    0.45
     אנ
    0.45
    トラ
    0.45
    ocratic
    0.45
     exige
    0.44
    殺
    0.44
     alive
    0.43
    Activations Density 0.001%

    No Known Activations