© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136476
    Prev
    Next
    INDEX
    Explanations

    building and design

    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
    まして
    0.48
    俶
    0.48
    嶅
    0.46
    कविता
    0.45
     cidade
    0.45
     prefecture
    0.43
     ولو
    0.43
    itsi
    0.43
    𝄞
    0.42
     Институт
    0.42
    POSITIVE LOGITS
    .
    0.55
    7
    0.49
     .
    0.47
    à
    0.46
    os
    0.44
     !
    0.43
     Cl
    0.41
    ing
    0.40
     SE
    0.38
     SP
    0.37
    Activations Density 0.007%

    No Known Activations