© 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. 73116
    Prev
    Next
    INDEX
    Explanations

    you to update

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

    aspect categories and workplace integration

    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
     such
    0.60
     RJ
    0.57
    .
    0.54
     wagons
    0.52
     krat
    0.52
     what
    0.49
     sacks
    0.49
     S
    0.48
     rys
    0.48
     ign
    0.48
    POSITIVE LOGITS
    仳
    0.48
    سوم
    0.48
    тування
    0.48
    ду
    0.47
    ᴜ
    0.47
    دی
    0.47
    љу
    0.47
    دي
    0.46
     ја
    0.46
     وزیراعظم
    0.45
    Activations Density 0.002%

    No Known Activations