© 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. 11953
    Prev
    Next
    INDEX
    Explanations

    and connectors

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

    word followed by and

    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
     sebagainya
    0.52
     hanging
    0.47
     march
    0.44
     plays
    0.42
    یں۔
    0.40
     টি
    0.40
    ?,?,
    0.40
     $)$.
    0.40
     itp
    0.39
     ہو۔
    0.39
    POSITIVE LOGITS
     અને
    1.16
     आणि
    1.13
     ਅਤੇ
    1.11
     và
    1.03
     ಮತ್ತು
    1.01
     እና
    1.00
     и
    0.97
     और
    0.97
     και
    0.97
     และ
    0.96
    Activations Density 0.233%

    No Known Activations