© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7323
    Prev
    Next
    INDEX
    Explanations

    Markdown formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     váš
    0.27
     reste
    0.24
     และ
    0.24
     slay
    0.23
    ོ
    0.23
     marques
    0.23
     rück
    0.22
     régions
    0.22
     respekt
    0.22
     précise
    0.21
    POSITIVE LOGITS
    Three
    0.27
    begin
    0.27
    The
    0.27
    P
    0.27
    Name
    0.26
    5
    0.26
    three
    0.26
    6
    0.26
     P
    0.25
    UN
    0.25
    Activations Density 0.409%

    No Known Activations