© 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. 149745
    Prev
    Next
    INDEX
    Explanations

    filtering out noise

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

    filter out or keep

    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
    s
    0.73
     sebagai
    0.59
    ی
    0.59
     as
    0.56
     bela
    0.55
    nya
    0.55
     sebuah
    0.55
     bookcase
    0.55
     arena
    0.54
     inhibitor
    0.54
    POSITIVE LOGITS
     Filt
    1.22
     Filter
    1.21
    过滤
    1.18
    doFilter
    1.18
    Filters
    1.16
    滤
    1.16
    Filter
    1.15
     Filters
    1.15
    filter
    1.13
     filtro
    1.13
    Activations Density 0.036%

    No Known Activations