© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203869
    Prev
    Next
    INDEX
    Explanations

    Microsoft AI and engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ہ
    0.48
    इसका
    0.48
     commuter
    0.45
     longueur
    0.45
    َح
    0.44
     commuters
    0.44
    ゐ
    0.44
     विराज
    0.42
     पार्षद
    0.42
     высоте
    0.42
    POSITIVE LOGITS
     הראש
    0.49
    ,
    0.45
     br
    0.43
     Kadar
    0.43
     desar
    0.43
     intravenously
    0.43
    Khe
    0.43
    Dict
    0.42
    Iron
    0.42
    Ked
    0.42
    Activations Density 0.002%

    No Known Activations