© 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. 2292
    Prev
    Next
    INDEX
    Explanations

    associated with / linked to

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

    linked to

    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
     قائمة
    0.44
    robots
    0.43
    眼中
    0.40
    0
    0.38
    𝟬
    0.38
    眼里
    0.37
    ög
    0.36
     позволяют
    0.36
     టీ
    0.36
     優
    0.35
    POSITIVE LOGITS
     connected
    0.81
     linked
    0.74
     associated
    0.73
     связан
    0.70
    linked
    0.68
    connected
    0.67
     tied
    0.66
    关联
    0.66
     związane
    0.66
     connect
    0.64
    Activations Density 0.191%

    No Known Activations