© 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. 78341
    Prev
    Next
    INDEX
    Explanations

    about

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

    autonomous robots

    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
    桃園
    0.44
    ",[],"
    0.43
    煖
    0.42
    ération
    0.41
    個別
    0.41
    avance
    0.40
    <0x0B>
    0.40
    近づ
    0.40
    ታ
    0.39
    փ
    0.39
    POSITIVE LOGITS
     atlet
    0.44
     Timor
    0.43
     peringkat
    0.42
    ｊ
    0.42
     gedaan
    0.42
     gases
    0.42
     Cyr
    0.41
     gjort
    0.41
     umur
    0.41
     مرگ
    0.41
    Activations Density 0.000%

    No Known Activations