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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 841
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation or verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hyperparameters
    0.87
     Lifecycle
    0.87
     convolutional
    0.86
     GitHub
    0.81
     사용자
    0.80
     Metadata
    0.79
     Workflow
    0.79
     Placeholder
    0.78
     Autodesk
    0.77
     Formatting
    0.76
    POSITIVE LOGITS
    ormous
    0.87
     sorrow
    0.85
     splendid
    0.80
     adore
    0.78
     shrewd
    0.77
    cheerful
    0.76
    astrous
    0.75
     arouse
    0.75
    oubt
    0.74
     admire
    0.74
    Activations Density 0.414%

    No Known Activations