© 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. 173627
    Prev
    Next
    INDEX
    Explanations

    system operation for host

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

    outcomes and limitations

    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
    5
    0.52
    1
    0.48
    are
    0.46
    6
    0.45
    othe
    0.45
    4
    0.45
    bb
    0.44
    ager
    0.42
    yna
    0.42
    8
    0.42
    POSITIVE LOGITS
     சூரிய
    0.54
     Austr
    0.54
    ിയെ
    0.49
     மேம்ப
    0.46
     disponibili
    0.46
    ENDOR
    0.45
     বৃদ্ধি
    0.45
     بابەت
    0.45
    ровой
    0.45
     ಮೂ
    0.44
    Activations Density 0.001%

    No Known Activations