© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12365
    Prev
    Next
    INDEX
    Explanations

    key: value pairs like "value": "04/24"

    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_40_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
    माइंडर
    0.37
    Ს
    0.34
    Პ
    0.33
    atthaya
    0.33
    মিনা
    0.33
    खास्त
    0.32
    ጠት
    0.32
    ?”.
    0.32
    worldly
    0.31
    AttributeInfo
    0.31
    POSITIVE LOGITS
    0.41
     similarly
    0.37
    '
    0.34
        
    0.34
     etc
    0.33
       
    0.33
    同様
    0.32
     Similarly
    0.31
     November
    0.31
     E
    0.31
    Activations Density 0.063%

    No Known Activations