© 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. 198476
    Prev
    Next
    INDEX
    Explanations

    time periods and specific groups

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

    often focus, watching these

    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
    t
    0.55
    我們的
    0.49
    details
    0.48
     മത്സ
    0.46
     unseres
    0.45
     李
    0.45
    tki
    0.44
    1
    0.44
    some
    0.43
     neuritis
    0.43
    POSITIVE LOGITS
    ۊ
    0.48
     sacar
    0.48
     पीडी
    0.46
     움직
    0.45
     باسک
    0.44
     अर्ध
    0.43
    ጩ
    0.42
    гү
    0.42
    ரும்பு
    0.42
    başı
    0.41
    Activations Density 0.000%

    No Known Activations