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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109955
    Prev
    Next
    INDEX
    Explanations

    Brazilian cities and states

    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
    矣
    -0.77
     profiling
    -0.72
    coherent
    -0.70
    ོད་
    -0.68
     pouvoir
    -0.68
    ffer
    -0.68
    沿い
    -0.68
    vett
    -0.66
    improve
    -0.66
    sists
    -0.66
    POSITIVE LOGITS
     phố
    0.92
     तुल
    0.86
     사람
    0.84
    שמי
    0.81
     dialec
    0.78
     GMO
    0.74
     avg
    0.74
    中学
    0.73
     avatars
    0.73
    зг
    0.72
    Activations Density 0.012%

    No Known Activations