© 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. 51606
    Prev
    Next
    INDEX
    Explanations

    provide annual report

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

    brands and services names

    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
     Mapa
    0.47
    ’;
    0.46
    ट्ट
    0.46
     Macbeth
    0.44
     Bên
    0.44
     возле
    0.44
     १६
    0.44
    otom
    0.44
     थरूर
    0.43
    olol
    0.43
    POSITIVE LOGITS
    ча
    0.50
    FILENAME
    0.47
    ية
    0.47
    ç
    0.47
    ំណ
    0.45
     nogen
    0.45
    يدا
    0.45
    ফ
    0.45
    आशा
    0.44
     راست
    0.43
    Activations Density 0.000%

    No Known Activations