© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    songs and blessings

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

    classification metrics and structured data

    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
     sawa
    0.46
    苺
    0.46
    వ్
    0.43
    水を
    0.42
    一周
    0.42
    ÃO
    0.41
     sols
    0.41
     ڕ
    0.40
     جذ
    0.40
     آپ
    0.40
    POSITIVE LOGITS
                                
    0.45
                          
    0.45
                        
    0.44
                            
    0.44
     Ruman
    0.43
                                  
    0.43
    gebracht
    0.42
                         
    0.40
                               
    0.40
     Franck
    0.40
    Activations Density 0.002%

    No Known Activations