© 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. 166173
    Prev
    Next
    INDEX
    Explanations

    search results and listings

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

    skill, guidance, programming

    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
     dodgy
    0.55
    hdd
    0.49
    drv
    0.46
    windows
    0.46
    ی
    0.45
    spectrum
    0.45
    hdu
    0.44
    ඇ
    0.44
     spectrum
    0.44
    imaging
    0.44
    POSITIVE LOGITS
     dịp
    0.53
     Gemeinschaft
    0.50
    seiten
    0.50
     Aktivitäten
    0.49
     اسی
    0.49
     Informe
    0.48
     Seiten
    0.47
     diario
    0.46
     ngư
    0.46
     dola
    0.46
    Activations Density 0.001%

    No Known Activations