© 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. 190236
    Prev
    Next
    INDEX
    Explanations

    years as, philosophical team

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

    Organizations, Foundations, team

    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
    依存
    0.54
    $
    0.51
    कर्म
    0.50
     ats
    0.50
    КА
    0.49
    ロッ
    0.48
    RECTION
    0.47
     أعلام
    0.47
     kategor
    0.46
    颓
    0.46
    POSITIVE LOGITS
     plausible
    0.48
     danger
    0.48
     predator
    0.47
    ită
    0.47
     somatic
    0.46
     stillness
    0.46
     fibro
    0.45
     mécan
    0.45
     plaus
    0.44
     mesh
    0.44
    Activations Density 0.001%

    No Known Activations