© 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. 156152
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific words

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

    number of years or capacity

    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
     chicken
    0.47
     terrestre
    0.44
     offense
    0.44
     Chicken
    0.43
    ाइब
    0.42
    殳
    0.42
     turtle
    0.42
     redistribution
    0.42
     Tooth
    0.42
    获
    0.42
    POSITIVE LOGITS
     TESTS
    0.50
    she
    0.49
     KENT
    0.48
    CHAPTER
    0.47
    tage
    0.46
     Список
    0.46
     KEN
    0.46
     मालिके
    0.46
    bergh
    0.46
     अध्याय
    0.46
    Activations Density 0.000%

    No Known Activations