© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108471
    Prev
    Next
    INDEX
    Explanations

    the followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     refirió
    -1.28
     zí
    -1.23
    vég
    -1.20
     llamaba
    -1.19
    inkl
    -1.18
     insiste
    -1.17
     hablaba
    -1.16
     ára
    -1.15
     bús
    -1.13
     parfü
    -1.13
    POSITIVE LOGITS
     each
    1.34
     otherwise
    1.31
     where
    1.25
     during
    1.14
     that
    1.11
     Otherwise
    1.09
     mỗi
    1.08
     there
    1.03
     respective
    1.02
    w
    1.02
    Activations Density 0.065%

    No Known Activations