© 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. 26940
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    numbers with units of time or measurement

    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
    %
    0.48
     for
    0.47
     বছরে
    0.46
     percent
    0.42
    %)
    0.42
     GY
    0.41
     envelop
    0.41
     \%$
    0.40
     $
    0.40
     ACTION
    0.40
    POSITIVE LOGITS
    lois
    0.45
     Віль
    0.43
     기다
    0.43
    尼斯
    0.41
     Kupfer
    0.41
     ہوئی۔
    0.40
     돌아
    0.39
    nish
    0.39
     препят
    0.38
     중에서
    0.38
    Activations Density 0.027%

    No Known Activations