© 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. 185839
    Prev
    Next
    INDEX
    Explanations

    individuals between

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

    specific concepts or foreign words

    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
    9
    0.51
    set
    0.48
    count
    0.48
    ville
    0.48
    bos
    0.47
    fox
    0.46
    os
    0.46
    object
    0.45
    {}
    0.45
    zone
    0.45
    POSITIVE LOGITS
    试验
    0.50
    觕
    0.49
     sufrir
    0.49
    食用
    0.49
    祷
    0.48
    岔
    0.47
     carbono
    0.47
    玷
    0.47
    协作
    0.46
     দুর্যোগ
    0.46
    Activations Density 0.000%

    No Known Activations