© 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. 122044
    Prev
    Next
    INDEX
    Explanations

    looking at or for

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

    numbers and technical terms

    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
     TO
    0.52
    )(
    0.48
    _
    0.48
     clear
    0.47
    )
    0.47
     NGO
    0.47
     podnik
    0.46
    Ready
    0.46
    TO
    0.46
    '
    0.45
    POSITIVE LOGITS
     என்னும்
    0.61
     overpowering
    0.59
    zechoslovakia
    0.55
    ግሎ
    0.54
     јед
    0.52
     نفسي
    0.52
     zwölf
    0.52
    電池
    0.50
     세포
    0.49
     ص
    0.49
    Activations Density 0.000%

    No Known Activations