© 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. 74410
    Prev
    Next
    INDEX
    Explanations

    reporting accident, number, US, supervising, essay

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

    specific names 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
     earnestly
    0.48
    ரியா
    0.46
    ೪
    0.46
     rhythmic
    0.46
     따
    0.45
     sighed
    0.44
    ouncil
    0.44
     ウォ
    0.44
    리아
    0.43
     empat
    0.43
    POSITIVE LOGITS
    azón
    0.47
     Gage
    0.45
    ná
    0.44
    вании
    0.43
    nö
    0.43
    gau
    0.43
     Iphone
    0.43
     könne
    0.42
    uz
    0.41
    t
    0.41
    Activations Density 0.001%

    No Known Activations