© 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. 41724
    Prev
    Next
    INDEX
    Explanations

    court, carnival, consumers

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

    technical documentation and concepts

    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
     subunits
    0.47
     NBC
    0.44
     গাঁ
    0.42
     Takeuchi
    0.42
     budgeted
    0.40
    鎊
    0.40
     इच्छ
    0.40
    bilder
    0.40
    __':
    0.39
     deliverables
    0.39
    POSITIVE LOGITS
    elize
    0.49
    Само
    0.48
    ll
    0.48
    Эти
    0.46
    Де
    0.45
    ole
    0.45
    Aile
    0.45
    //
    0.45
    Е
    0.45
    Г
    0.44
    Activations Density 0.001%

    No Known Activations