© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 179437
    Prev
    Next
    INDEX
    Explanations

    publications and exclamations

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

    solar flare static, every day

    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
    เสริม
    0.54
    นอก
    0.49
    ση
    0.48
    рель
    0.47
    𝔪
    0.46
    颍
    0.45
    cS
    0.45
    ʋ
    0.45
    กำ
    0.44
    렐
    0.44
    POSITIVE LOGITS
     
    0.51
     inventories
    0.45
     catalogs
    0.45
     cabinets
    0.44
     cosplay
    0.43
     شويه
    0.42
     launched
    0.41
    onces
    0.41
     urlpatterns
    0.41
     award
    0.40
    Activations Density 0.000%

    No Known Activations