© 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. 133438
    Prev
    Next
    INDEX
    Explanations

    prepositions and common words

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

    Improved GUI, archive, suggests delay

    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
    stamp
    0.51
    open
    0.51
    nb
    0.51
     contesto
    0.50
    প
    0.50
    max
    0.49
    IN
    0.47
    uno
    0.47
    relay
    0.47
    pt
    0.46
    POSITIVE LOGITS
     Frankly
    0.46
    羡
    0.46
     nhiêu
    0.45
    逖
    0.45
    䫒
    0.44
     ой
    0.44
     ugyan
    0.44
    קת
    0.44
     Architektur
    0.43
     lẫn
    0.43
    Activations Density 0.000%

    No Known Activations