© 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. 10445
    Prev
    Next
    INDEX
    Explanations

    linking corresponding items

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

    respectively

    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
     effectuer
    0.61
     మాత్రం
    0.61
     équipe
    0.59
    ແລະ
    0.58
     Yvonne
    0.58
     谢
    0.58
     appareil
    0.56
     rétréci
    0.55
    ിയെ
    0.55
    <unused364>
    0.54
    POSITIVE LOGITS
    ed
    0.57
    ii
    0.52
    々の
    0.52
    were
    0.50
    ли
    0.49
    ’
    0.49
     were
    0.48
    तः
    0.47
    di
    0.47
    τη
    0.47
    Activations Density 0.014%

    No Known Activations