© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 237466
    Prev
    Next
    INDEX
    Explanations

    pencils mental

    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
    Ange
    0.41
    )]
    0.41
    giant
    0.40
     यू
    0.40
    強
    0.39
     sprechen
    0.39
     ತಿಳ
    0.38
     આપી
    0.38
    MgCl
    0.38
    加
    0.38
    POSITIVE LOGITS
     Crimea
    0.50
    ؛
    0.49
    <0x98>
    0.49
     insecticide
    0.47
     comerciales
    0.46
    ceased
    0.44
     pompa
    0.44
     Pestic
    0.43
     Noticias
    0.43
     quantidades
    0.43
    Activations Density 0.001%

    No Known Activations