© 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. 169837
    Prev
    Next
    INDEX
    Explanations

    goal Pioneers

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

    featuring attractive

    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
    ә
    0.49
    મ
    0.48
    र
    0.47
     serait
    0.46
    嬛
    0.46
    werte
    0.46
    м
    0.45
    ̉
    0.44
    ૨
    0.44
    ર
    0.43
    POSITIVE LOGITS
     subiect
    0.47
     disruptions
    0.46
     jewel
    0.46
     تول
    0.45
     sharks
    0.44
     medics
    0.44
     analysts
    0.44
     fieldwork
    0.44
     ორგანო
    0.44
     hypogly
    0.43
    Activations Density 0.001%

    No Known Activations