© 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. 136596
    Prev
    Next
    INDEX
    Explanations

    raised from the dead, upcoming events

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

    property | Voice | app | dictionary

    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
    Analyzer
    0.48
     radiologists
    0.45
     ఫి
    0.45
    ز
    0.44
    ћ
    0.43
    
    0.43
    ли
    0.42
     radiographic
    0.42
    isted
    0.42
    ћи
    0.41
    POSITIVE LOGITS
     résident
    0.47
     mů
    0.47
    sembl
    0.46
    മം
    0.45
     Fhir
    0.45
     béton
    0.45
    뭣
    0.44
     biznes
    0.44
     punk
    0.44
    देशी
    0.43
    Activations Density 0.001%

    No Known Activations