© 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. 243449
    Prev
    Next
    INDEX
    Explanations

    recently held

    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
    일
    0.54
    से
    0.52
    ми
    0.52
    ใ
    0.50
    का
    0.49
    یک
    0.48
    ре
    0.48
    ای
    0.47
    푸
    0.47
    풀
    0.46
    POSITIVE LOGITS
     okra
    0.56
     arrives
    0.54
     conform
    0.54
     cranberries
    0.54
     segreg
    0.52
     raspberries
    0.52
     megfelel
    0.51
    ografie
    0.50
     flyer
    0.50
     rosé
    0.50
    Activations Density 0.000%

    No Known Activations