© 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. 126097
    Prev
    Next
    INDEX
    Explanations

    rather than, one of

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

    history and context

    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
    <0xE1>
    0.59
    assy
    0.54
    AH
    0.51
    æ
    0.51
    AI
    0.48
    jik
    0.48
    ASS
    0.48
    ā
    0.48
    yt
    0.47
    ret
    0.47
    POSITIVE LOGITS
    푐
    0.54
    ोष
    0.53
    лении
    0.53
    인은
    0.52
     ingresos
    0.51
     ofthe
    0.51
     quà
    0.51
     funções
    0.50
    乆
    0.50
    resultados
    0.50
    Activations Density 0.000%

    No Known Activations