© 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. 211312
    Prev
    Next
    INDEX
    Explanations

    recently sacked, expenses, organist, by word

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

    quickest and easy options

    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
    ও
    0.46
    с
    0.46
    TH
    0.45
    đ
    0.45
    ના
    0.43
     srand
    0.42
    ধ
    0.41
    old
    0.41
    क
    0.41
    カ
    0.40
    POSITIVE LOGITS
    Ტ
    0.52
     Lemb
    0.49
    خصة
    0.46
     beschikbaar
    0.46
    سطس
    0.45
     Mitarbeit
    0.44
     fornece
    0.44
    िडेट
    0.43
     Тя
    0.43
     डा
    0.43
    Activations Density 0.000%

    No Known Activations