© 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. 87837
    Prev
    Next
    INDEX
    Explanations

    seeking more information

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

    more information, help, or opposite

    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
     এবং
    0.43
    ]+\
    0.43
     Soup
    0.43
     sectional
    0.42
     exchanged
    0.41
    =?,
    0.41
     or
    0.41
     necessary
    0.41
     ແລະ
    0.41
    Cage
    0.41
    POSITIVE LOGITS
     alguns
    0.59
     bazı
    0.50
     temos
    0.48
    г
    0.47
    ین
    0.46
     rougeâtre
    0.46
     tradiz
    0.46
     algunas
    0.46
    ്യ
    0.46
     wyniki
    0.46
    Activations Density 0.000%

    No Known Activations