© 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. 152432
    Prev
    Next
    INDEX
    Explanations

    preposition linking to noun/proper noun

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

    numbered lists

    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
    moder
    0.54
    oleans
    0.45
    ő
    0.45
     alegría
    0.45
    ෲ
    0.44
    ín
    0.44
    ínas
    0.44
    zada
    0.44
    와
    0.43
    Moder
    0.43
    POSITIVE LOGITS
     достиг
    0.52
    দ্বিতীয়
    0.51
     atteindre
    0.49
     transfection
    0.49
     moneys
    0.47
     secure
    0.46
     aeg
    0.45
     thicken
    0.45
     sempurna
    0.45
     উপমহাদেশ
    0.44
    Activations Density 0.001%

    No Known Activations