© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36239
    Prev
    Next
    INDEX
    Explanations

    classification and machine learning

    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_40_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
     sinuses
    0.38
     skewers
    0.37
    ୁ
    0.36
     Paren
    0.36
    想起
    0.36
    ῦ
    0.36
    向
    0.36
     Peng
    0.35
    caler
    0.35
    uduk
    0.35
    POSITIVE LOGITS
     minus
    0.44
     gets
    0.42
    comps
    0.42
    мента
    0.40
    xb
    0.39
    ));
    0.38
    তাসীন
    0.38
     działal
    0.38
    mes
    0.37
     реали
    0.37
    Activations Density 0.000%

    No Known Activations