© 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. 59439
    Prev
    Next
    INDEX
    Explanations

    located close

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

    Spanish conquistadors, 15th century

    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
     Dyke
    0.42
     Carr
    0.42
     дъ
    0.40
     carr
    0.40
     Continuum
    0.40
     Oak
    0.39
    氹
    0.39
     arr
    0.39
     Addison
    0.39
     Tuscan
    0.39
    POSITIVE LOGITS
    beqz
    0.47
    💢
    0.46
     സാഹചര്യ
    0.42
    keV
    0.42
     bhavanti
    0.41
    industrie
    0.40
    答案
    0.40
    permut
    0.39
     wonders
    0.39
    ための
    0.39
    Activations Density 0.016%

    No Known Activations