© 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. 102565
    Prev
    Next
    INDEX
    Explanations

    Island surroundings

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

    challenges & limited features

    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
     sb
    0.54
    ing
    0.53
    와
    0.48
    event
    0.46
    regex
    0.46
    :
    0.45
     sectors
    0.45
    ة
    0.45
     dulu
    0.45
    ọ
    0.45
    POSITIVE LOGITS
     helfen
    0.48
     ಆಧ
    0.48
     বী
    0.47
     لان
    0.47
    LuaPush
    0.46
     ಆದ್ದರಿಂದ
    0.45
     помога
    0.44
     deshalb
    0.44
     विधे
    0.44
     Ско
    0.43
    Activations Density 0.001%

    No Known Activations