© 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. 221316
    Prev
    Next
    INDEX
    Explanations

    pandas data type checks

    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
    
    0.43
     ordinary
    0.42
    േയ
    0.41
    Resize
    0.38
     evicted
    0.38
    resize
    0.37
    ROWN
    0.37
     modus
    0.37
     transport
    0.36
    Abasis
    0.36
    POSITIVE LOGITS
    sadpoetry
    0.42
    ᱱ
    0.39
    mersible
    0.38
    仍
    0.38
    '>";
    0.38
     JH
    0.37
    mgr
    0.37
    ')";
    0.37
    newToken
    0.37
     dormir
    0.36
    Activations Density 0.004%

    No Known Activations