© 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. 43622
    Prev
    Next
    INDEX
    Explanations

    when + most

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

    numbers after symbols

    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
    叁
    0.52
    鳝
    0.49
    ጴ
    0.49
    নাম
    0.42
    краё
    0.41
     বাহিরে
    0.41
    十八
    0.41
    ोरा
    0.40
    प्पू
    0.40
    शिवम
    0.40
    POSITIVE LOGITS
     incipient
    0.53
     (
    0.51
     devient
    0.47
     verhindert
    0.46
    に対する
    0.45
     fanciful
    0.45
     becom
    0.44
     (=
    0.44
     gef
    0.44
     timid
    0.44
    Activations Density 0.000%

    No Known Activations