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. 7886
    Prev
    Next
    INDEX
    Explanations

    code and state

    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
     rossi
    -0.79
     temb
    -0.77
    倞
    -0.75
     communiquez
    -0.72
    Notae
    -0.72
    ême
    -0.72
    Dimensioni
    -0.72
    Particles
    -0.71
     Depuis
    -0.71
     miy
    -0.70
    POSITIVE LOGITS
     State
    0.99
     state
    0.98
     states
    0.85
    𝓾
    0.79
    ölker
    0.79
     defecto
    0.78
    外国
    0.77
     berkualitas
    0.77
    чению
    0.77
    сий
    0.75
    Activations Density 0.001%

    No Known Activations