© 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. 10-GEMMASCOPE-RES-131K
    7. 112033
    Prev
    Next
    INDEX
    Explanations

    categories, year, win, vividly

    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
    </h1>
    -1.53
     to
    -1.48
     vooral
    -1.34
     другие
    -1.28
     werden
    -1.25
     &
    -1.23
     Gespräche
    -1.23
     itself
    -1.20
     essere
    -1.19
     versus
    -1.19
    POSITIVE LOGITS
    都已经
    1.45
    ኙ
    1.36
     所有
    1.32
    v
    1.25
    Trat
    1.24
    timmung
    1.24
     risolvere
    1.22
    ALTH
    1.22
     destul
    1.21
    句话
    1.20
    Activations Density 0.010%

    No Known Activations