© 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. 195114
    Prev
    Next
    INDEX
    Explanations

    some, various

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

    AI, Angels, Facebook, classification

    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
                            
    0.50
    Yok
    0.45
                                   
    0.45
    パターン
    0.44
    <u>
    0.43
            
    0.42
    ocytes
    0.42
    ął
    0.42
                                
    0.41
    +\
    0.41
    POSITIVE LOGITS
     některé
    0.56
     niektó
    0.50
     некоторые
    0.49
    鲜
    0.47
     fotografie
    0.47
     TRANSPORTURI
    0.47
     някои
    0.46
     stek
    0.46
     Ernährung
    0.45
     Виктор
    0.45
    Activations Density 0.001%

    No Known Activations