© 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. 75285
    Prev
    Next
    INDEX
    Explanations

    promote projects or aims

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

    promote innovation

    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
    很少
    0.47
    和
    0.43
     Annapolis
    0.40
     الكلام
    0.40
    ****
    0.39
    ENSES
    0.39
    **************
    0.39
    思想
    0.39
    ，
    0.39
    缄
    0.38
    POSITIVE LOGITS
     じゃん
    0.45
    maschine
    0.44
     বিনাম
    0.44
    アダ
    0.44
     refinements
    0.43
    ਫ
    0.43
     žele
    0.42
     হইয়৷
    0.42
     کھ
    0.42
     توسیع
    0.42
    Activations Density 0.002%

    No Known Activations