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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8128
    Prev
    Next
    INDEX
    Explanations

    international cricket contexts

    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
     청
    -0.85
     nationwide
    -0.84
     importation
    -0.76
    gdx
    -0.75
    霄
    -0.71
     Opening
    -0.71
    Complaints
    -0.70
     є
    -0.69
     opens
    -0.69
     European
    -0.69
    POSITIVE LOGITS
    olde
    0.95
    achs
    0.93
    锃
    0.85
    📫
    0.84
     cuchara
    0.82
     ICC
    0.81
    Singer
    0.79
    umbent
    0.79
    WEEN
    0.79
    ardt
    0.79
    Activations Density 0.016%

    No Known Activations