© 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. 149127
    Prev
    Next
    INDEX
    Explanations

    grace, DHCP, camera, asking

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

    machines, robot, teacher

    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
    루
    0.63
    ハンド
    0.54
    CDM
    0.54
    르
    0.52
    𝒎
    0.51
    리스마
    0.50
     lê
    0.49
    ل
    0.49
    리아
    0.48
    ம்ம
    0.48
    POSITIVE LOGITS
    men
    0.55
    mas
    0.51
    asser
    0.47
    </
    0.47
    den
    0.46
     providers
    0.46
    dataSource
    0.46
    inj
    0.45
    utscher
    0.45
     financially
    0.44
    Activations Density 0.000%

    No Known Activations