© 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. 124390
    Prev
    Next
    INDEX
    Explanations

    related to biological structures

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

    names and their history

    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
    єї
    0.47
    ag
    0.47
     controlar
    0.45
     প্রধান
    0.43
    গ
    0.43
     আম
    0.43
     ogran
    0.42
    钢琴
    0.42
     créée
    0.42
    াই
    0.42
    POSITIVE LOGITS
     tubules
    0.60
    젊
    0.52
     combustibles
    0.51
     scaff
    0.48
     toiletries
    0.47
     scaffolds
    0.47
     punctures
    0.46
     manglid
    0.46
     sete
    0.45
     misconceptions
    0.44
    Activations Density 0.000%

    No Known Activations