© 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. 104807
    Prev
    Next
    INDEX
    Explanations

    LORD of hosts

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

    depends on what

    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
    っていて
    0.50
    시켜
    0.48
     venous
    0.45
    동
    0.43
     खाता
    0.43
     öt
    0.43
     выну
    0.43
    시키
    0.42
     Infantil
    0.42
    시
    0.42
    POSITIVE LOGITS
     Construction
    0.55
    h
    0.51
    ANCED
    0.48
     Songs
    0.48
     SONGS
    0.47
     Fast
    0.45
     Inquiry
    0.45
     renovations
    0.45
     Journals
    0.44
    एलबी
    0.44
    Activations Density 0.002%

    No Known Activations