© 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. 11996
    Prev
    Next
    INDEX
    Explanations

    official announcements and events

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

    model trained by Google

    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
    밂
    0.50
    พี่
    0.41
    getLong
    0.41
     powerAll
    0.40
     manslaughter
    0.39
    শো
    0.38
    acariy
    0.38
    နိုင်သည်။
    0.38
    ป
    0.38
    নৈতিক
    0.38
    POSITIVE LOGITS
                 
    0.45
       
    0.44
                
    0.42
     dieses
    0.41
     adjectives
    0.41
     type
    0.41
        
    0.40
     olup
    0.39
     at
    0.39
     processed
    0.39
    Activations Density 0.060%

    No Known Activations