© 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. 109938
    Prev
    Next
    INDEX
    Explanations

    speaker tags or direct speech

    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
     کمپنی
    0.46
     serviço
    0.45
     बढ़िया
    0.45
    বিরোধী
    0.44
    不錯
    0.44
    詿
    0.44
     कामकाजी
    0.44
    zeczytaj
    0.44
     좋다
    0.43
     اچھی
    0.43
    POSITIVE LOGITS
    0.44
    >>
    0.42
     angr
    0.42
    $
    0.42
    )-
    0.42
     literalmente
    0.41
    3
    0.41
     waardoor
    0.41
     এতটাই
    0.40
     t
    0.40
    Activations Density 0.009%

    No Known Activations