© 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. 10-GEMMASCOPE-RES-131K
    7. 113379
    Prev
    Next
    INDEX
    Explanations

    highest degree adjectives

    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_10/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
    e
    -4.84
    i
    -3.55
    a
    -2.69
    or
    -2.61
    ed
    -2.58
    ㈫
    -2.50
    s
    -2.34
    u
    -2.31
    mathrm
    -2.22
    c
    -2.22
    POSITIVE LOGITS
    ︲
    2.77
    聼
    2.66
    zembro
    2.53
    愎
    2.42
     purest
    2.42
    聍
    2.38
     —
    2.36
     saddest
    2.34
    
    2.33
    ⚣
    2.31
    Activations Density 0.014%

    No Known Activations