© 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. 2616
    Prev
    Next
    INDEX
    Explanations

    verbs indicating an attempt

    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
     великолеп
    -1.55
     餐廳
    -1.37
     которы
    -1.29
     mewah
    -1.28
     môžu
    -1.26
    recently
    -1.25
    ῤ
    -1.23
     adelant
    -1.22
     publicités
    -1.21
    ığında
    -1.21
    POSITIVE LOGITS
     use
    1.93
     see
    1.83
     know
    1.79
     tell
    1.68
     help
    1.60
     purchase
    1.59
     get
    1.59
     do
    1.58
     ask
    1.54
     learn
    1.53
    Activations Density 0.191%

    No Known Activations