© 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. 169075
    Prev
    Next
    INDEX
    Explanations

    display them

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

    distinguishing categories

    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
    ▛
    0.50
    一股
    0.46
    计
    0.43
    让
    0.43
     短
    0.42
    极
    0.42
     给
    0.41
     Confidential
    0.41
    搽
    0.41
    饿
    0.41
    POSITIVE LOGITS
     tachy
    0.46
     diferenci
    0.44
     literals
    0.44
    चाकी
    0.44
     dioxygen
    0.44
     numeracy
    0.44
     inhomogeneous
    0.43
     distin
    0.43
     clonal
    0.43
     alleles
    0.43
    Activations Density 0.000%

    No Known Activations