Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7847
    Prev
    Next
    INDEX
    Explanations

    geographical names and technical terms

    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
     تغذ
    -0.84
     xmin
    -0.83
    Finger
    -0.82
    Phrase
    -0.78
     onlyOwner
    -0.77
    Bounds
    -0.77
    引言
    -0.76
    漿
    -0.74
     卧室
    -0.74
     Harm
    -0.73
    POSITIVE LOGITS
    Torino
    0.84
    Dinosaur
    0.80
    худ
    0.78
    ↵
    0.75
    Gotham
    0.75
    Schöne
    0.72
    Uwe
    0.71
    Opinions
    0.71
     Descripción
    0.71
    中の
    0.71
    Activations Density 0.008%

    No Known Activations