© 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. 162787
    Prev
    Next
    INDEX
    Explanations

    words in specific contexts

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

    modern world observations

    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
    Tickets
    0.47
    שהו
    0.47
     شوق
    0.47
    اتھ
    0.46
    Hearts
    0.42
     palk
    0.42
    碚
    0.42
     universitario
    0.41
    管理局
    0.41
    营收
    0.41
    POSITIVE LOGITS
     (=
    0.50
    usetzen
    0.48
     („
    0.47
     («
    0.45
     ап
    0.45
    」（
    0.44
     $($
    0.44
     caregivers
    0.44
     [$
    0.44
    🩺
    0.44
    Activations Density 0.001%

    No Known Activations