© 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. 34-GEMMASCOPE-RES-131K
    4. 110604
    Prev
    Next
    INDEX
    Explanations

    NOTICE file

    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
     Saleh
    -0.83
    ﺐ
    -0.71
    Unavailable
    -0.68
     パーツ
    -0.67
    creas
    -0.66
    ээ
    -0.66
    anglès
    -0.66
    étaient
    -0.66
     Harsh
    -0.66
    getUrl
    -0.65
    POSITIVE LOGITS
     edge
    0.89
     CV
    0.82
    CV
    0.75
    剥が
    0.73
    edge
    0.73
     mante
    0.71
    ợi
    0.69
     runner
    0.68
     fundamentals
    0.68
    Themen
    0.68
    Activations Density 0.074%

    No Known Activations