© 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. 204032
    Prev
    Next
    INDEX
    Explanations

    past recurring conditions

    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
     നേരി
    0.44
    广播
    0.43
     توڑ
    0.43
    吨
    0.43
     곱
    0.42
     endearing
    0.41
     çarp
    0.41
     nared
    0.39
     متجه
    0.39
    USH
    0.39
    POSITIVE LOGITS
     foram
    0.47
    ↵↵
    0.47
     Credits
    0.45
    Finalmente
    0.44
     Cari
    0.44
    Four
    0.44
     Eras
    0.44
     Difficult
    0.44
    b
    0.44
     fue
    0.43
    Activations Density 0.001%

    No Known Activations