© 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. 63819
    Prev
    Next
    INDEX
    Explanations

    adverbs of certainty or frequency

    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
    敺
    -1.69
    brakk
    -1.66
    　　[
    -1.63
    decoración
    -1.61
     juſ
    -1.61
    黥
    -1.59
     incrí
    -1.59
    ⃤
    -1.57
     rése
    -1.56
     sapatos
    -1.56
    POSITIVE LOGITS
     be
    4.56
     have
    2.53
    P
    1.89
    B
    1.89
    C
    1.88
    be
    1.86
    M
    1.85
     make
    1.85
    l
    1.84
    But
    1.83
    Activations Density 0.095%

    No Known Activations