© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 74968
    Prev
    Next
    INDEX
    Explanations

    World Communion

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

    why followed by explanations

    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
    ту
    0.55
    то
    0.54
    йс
    0.53
    тана
    0.52
    та
    0.52
    й
    0.51
    ўні
    0.51
    но
    0.49
     поступа
    0.48
    fez
    0.48
    POSITIVE LOGITS
     विषयों
    0.46
     Sands
    0.46
     विषय
    0.45
     uncanny
    0.45
     Bacterial
    0.44
    iments
    0.43
    }}-
    0.42
    degenerative
    0.42
     Blood
    0.41
     কট
    0.41
    Activations Density 0.000%

    No Known Activations