© 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. 136528
    Prev
    Next
    INDEX
    Explanations

    analytics tab or web links

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

    asking to analyze or explain

    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
     मि
    0.55
    at
    0.54
     बा
    0.51
    posable
    0.46
    ミ
    0.46
     svar
    0.45
    ves
    0.45
     पांव
    0.45
    於
    0.44
    plit
    0.44
    POSITIVE LOGITS
     سلاټ
    0.50
     médicament
    0.48
     fijn
    0.48
    )");
    0.47
     لیګ
    0.46
    ソル
    0.46
    هَا
    0.46
     uitgenodigd
    0.46
     arrondi
    0.45
     فونیټ
    0.44
    Activations Density 0.001%

    No Known Activations