© 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. 101237
    Prev
    Next
    INDEX
    Explanations

    related to .ed and through

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

    structuring code and text elements

    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
     そして
    0.60
     devemos
    0.52
    י
    0.52
     П
    0.47
     इस्तीफा
    0.47
     ある
    0.47
     подарок
    0.47
     ケ
    0.46
     accompl
    0.46
     オ
    0.46
    POSITIVE LOGITS
    carrot
    0.50
    alien
    0.45
     bog
    0.44
    缕
    0.42
    similar
    0.42
    );\
    0.41
    bog
    0.41
    保证金
    0.41
     calyc
    0.41
    bau
    0.40
    Activations Density 0.000%

    No Known Activations