© 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. 105654
    Prev
    Next
    INDEX
    Explanations

    specific descriptions

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

    advance planning

    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
    意義
    0.52
    зона
    0.43
    َة
    0.42
    屯
    0.40
    辯
    0.40
     तेरी
    0.40
    ಸ್
    0.40
    聽到
    0.39
     womb
    0.39
     AREAS
    0.39
    POSITIVE LOGITS
    Ji
    0.50
    marginStart
    0.50
    with
    0.50
    U
    0.49
     Jing
    0.48
     with
    0.47
    daemon
    0.47
     glist
    0.47
     Ji
    0.46
    Ki
    0.46
    Activations Density 0.001%

    No Known Activations