© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117525
    Prev
    Next
    INDEX
    Explanations

    adjectives before 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
    瑒
    -1.44
    鲥
    -1.41
     prêtre
    -1.41
    ᠁
    -1.34
     bienfaits
    -1.34
    紅茶
    -1.34
     évêque
    -1.34
    虜
    -1.33
    ⛦
    -1.31
    Elisa
    -1.29
    POSITIVE LOGITS
     and
    2.50
     It
    1.30
    様な
    1.21
    気がします
    1.18
     The
    1.13
    many
    1.13
     Its
    1.12
     or
    1.11
     They
    1.10
    with
    1.09
    Activations Density 0.398%

    No Known Activations