© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8954
    Prev
    Next
    INDEX
    Explanations

    a breakdown, JSON, vibe, sentence, formula

    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_9_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
     ($\
    1.05
    Potion
    0.98
    <unused289>
    0.92
    paused
    0.91
     swipe
    0.90
     sbag
    0.90
    ́p
    0.89
    bake
    0.88
     caract
    0.87
     segit
    0.87
    POSITIVE LOGITS
    1.11
     বুধবার
    0.95
     century
    0.95
     centuries
    0.94
     conifers
    0.93
     scholarly
    0.90
     broader
    0.90
    і
    0.89
     среду
    0.89
    ění
    0.89
    Activations Density 0.998%

    No Known Activations