© 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. 142016
    Prev
    Next
    INDEX
    Explanations

    reading and saying

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

    Instagram, LCD, Crime, advancements, C

    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
     Croatia
    0.54
     FAO
    0.52
    姮
    0.51
     Gael
    0.50
     Vector
    0.50
     เว
    0.50
     bestow
    0.49
     CSO
    0.49
     Listo
    0.49
     Verona
    0.49
    POSITIVE LOGITS
    dm
    0.59
    ungs
    0.55
    ya
    0.54
    ám
    0.54
    dp
    0.52
    dal
    0.52
    ating
    0.51
    ą
    0.51
    iff
    0.51
    arks
    0.51
    Activations Density 0.001%

    No Known Activations