© 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. 176119
    Prev
    Next
    INDEX
    Explanations

    contact by telephone

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

    relies on, paper documents, quality issues

    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
    やかな
    0.50
    ettha
    0.47
     ลักษณะ
    0.47
    闓
    0.46
    したがって
    0.45
     মৃত্যুর
    0.44
    Stylesheet
    0.44
     要求
    0.43
     मुख्यतः
    0.43
    ligence
    0.43
    POSITIVE LOGITS
     érté
    0.43
    Despatx
    0.41
    IVO
    0.40
    ອ
    0.39
    ALL
    0.39
     differentially
    0.39
    VALUES
    0.38
     ON
    0.38
     değer
    0.38
    ACY
    0.38
    Activations Density 0.001%

    No Known Activations