© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104968
    Prev
    Next
    INDEX
    Explanations

    which + capability verb

    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
     to
    -1.61
    brtc
    -1.52
     mám
    -1.51
    However
    -1.50
    asantry
    -1.48
    𖤣
    -1.38
     дуже
    -1.38
    amitié
    -1.36
     örgü
    -1.35
    extré
    -1.34
    POSITIVE LOGITS
     you
    1.88
     which
    1.64
    dits
    1.59
     οποία
    1.45
    🫣
    1.41
     мало
    1.37
     ingles
    1.34
    </em>
    1.34
    .
    1.34
    følge
    1.31
    Activations Density 0.010%

    No Known Activations