© 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. 83187
    Prev
    Next
    INDEX
    Explanations

    or as alternatives

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

    is called

    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
    或者是
    0.45
    ätten
    0.43
    或者
    0.43
     alebo
    0.42
    лите
    0.42
    Comté
    0.42
    jonen
    0.41
    或
    0.41
     లేదా
    0.41
    或是
    0.40
    POSITIVE LOGITS
     миллионов
    0.49
     mètres
    0.46
     millones
    0.45
    ್‌
    0.44
    レコード
    0.44
     yearling
    0.44
     மேற்பர
    0.43
     má
    0.42
     ಎರಡು
    0.42
     basit
    0.42
    Activations Density 0.000%

    No Known Activations