© 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. 117412
    Prev
    Next
    INDEX
    Explanations

    futureuntil

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

    hover, modules, planets

    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
    們
    0.49
     shēng
    0.46
    game
    0.43
    Game
    0.43
    Customer
    0.43
    4
    0.42
    還要
    0.41
    A
    0.41
    Volume
    0.40
    兩
    0.40
    POSITIVE LOGITS
     pecado
    0.50
    یاء
    0.49
     cuch
    0.48
     utilizado
    0.47
     verwend
    0.46
    ्यूट
    0.45
     परीक्ष
    0.45
     conquistar
    0.45
     fearless
    0.45
    िति
    0.45
    Activations Density 0.001%

    No Known Activations