© 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. 32190
    Prev
    Next
    INDEX
    Explanations

    Indus Valley, Harappa, advanced urban

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

    ancient urban planning 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
     ідэ
    0.49
     層
    0.46
    LECTION
    0.46
    Selection
    0.44
     Гуляць
    0.44
    зий
    0.44
     மொழ
    0.44
    nać
    0.43
    ్యం
    0.43
     BUFFER
    0.43
    POSITIVE LOGITS
     Kembali
    0.52
    n
    0.51
     Steam
    0.45
     signifikan
    0.44
    ce
    0.44
     soybeans
    0.43
    नमस्कार
    0.43
    收益
    0.43
    期货
    0.42
    💸
    0.42
    Activations Density 0.000%

    No Known Activations