© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 224306
    Prev
    Next
    INDEX
    Explanations

    references, explanations, and lists

    np_acts-logits-general · gemini-2.5-flash-lite

    PDF like written disorder being about . Basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     گزشتہ
    0.49
     HNO
    0.48
     WUE
    0.46
     NOx
    0.46
     refundable
    0.45
    ✼
    0.45
     NHT
    0.45
     TMP
    0.44
     Maintains
    0.43
    TMP
    0.43
    POSITIVE LOGITS
     Weiner
    0.49
     বিজনেস
    0.45
     Heroes
    0.44
     Vorteil
    0.44
     Drucker
    0.44
    电视
    0.43
    éri
    0.43
    CTAssert
    0.43
    硋
    0.43
     blancs
    0.42
    Activations Density 0.001%

    No Known Activations