© 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. 10732
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    parts of common phrases

    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
     murderous
    0.27
    ੪
    0.26
    意志
    0.23
     తన
    0.23
    न्ध
    0.23
    她的
    0.22
     തോ
    0.22
    political
    0.21
     Siti
    0.21
     அவள்
    0.21
    POSITIVE LOGITS
    /
    0.37
     која
    0.30
     которые
    0.29
     that
    0.27
     које
    0.27
    ,
    0.26
     которое
    0.26
    ，
    0.25
    –
    0.25
     ajustable
    0.25
    Activations Density 0.766%

    No Known Activations