© 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. 63901
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and ideas

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

    constructs or fictions

    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
    титься
    0.46
    صیٰ
    0.46
    ወት
    0.44
    སྐ
    0.44
    鸳
    0.42
     nonchal
    0.41
    ӣ
    0.40
     मछली
    0.40
    ərbay
    0.40
    囤
    0.40
    POSITIVE LOGITS
    arth
    0.47
     Whose
    0.46
     Useful
    0.45
     manifestation
    0.45
     unparalleled
    0.45
     whose
    0.44
    !";
    0.44
    isations
    0.43
    !
    0.42
    ants
    0.42
    Activations Density 0.026%

    No Known Activations