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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 636
    Prev
    Next
    INDEX
    Explanations

    verbs for action or completion

    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
     than
    -1.54
     since
    -1.49
    </h2>
    -1.41
     więc
    -1.40
     being
    -1.38
     therefore
    -1.33
     tej
    -1.23
     this
    -1.23
     also
    -1.21
     lettore
    -1.20
    POSITIVE LOGITS
     одной
    1.27
     språk
    1.26
    鶿
    1.21
     darbu
    1.20
    られている
    1.19
     säs
    1.19
     situe
    1.18
     maž
    1.18
    merken
    1.16
    =[];
    
    1.13
    Activations Density 0.177%

    No Known Activations