© 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. 231453
    Prev
    Next
    INDEX
    Explanations

    fairy tales

    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
     Wednesday
    0.46
     alebo
    0.43
     Kindergarten
    0.43
     School
    0.42
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.42
     Ln
    0.41
     students
    0.41
     Quarry
    0.41
    ↵↵↵
    0.41
     Rutherford
    0.41
    POSITIVE LOGITS
     излу
    0.47
     દર્
    0.42
     міжнарод
    0.41
     ин
    0.41
     дове
    0.40
     איך
    0.40
    éviter
    0.40
     континен
    0.40
     emisión
    0.40
    বিশ্বাস
    0.39
    Activations Density 0.000%

    No Known Activations