© 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. 128928
    Prev
    Next
    INDEX
    Explanations

    Borussia Mönchengladbach

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

    range and specific values

    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
    희
    0.50
    함
    0.48
    琤
    0.48
    чку
    0.47
     주변
    0.47
    다
    0.47
     қ
    0.47
    心配
    0.47
    坤
    0.46
    да
    0.46
    POSITIVE LOGITS
     engagements
    0.57
    :
    0.51
     actionable
    0.50
     infidelity
    0.49
    ars
    0.48
    engines
    0.47
     শত্র
    0.46
     carbohyd
    0.46
    🎣
    0.45
    istance
    0.45
    Activations Density 0.001%

    No Known Activations