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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155485
    Prev
    Next
    INDEX
    Explanations

    juvenile arthritis

    np_acts-logits-general · gemini-2.5-flash-lite

    market solely through internal resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     לא
    0.54
     הכ
    0.49
     מת
    0.49
     =[
    0.48
     захід
    0.47
     מס
    0.47
     огром
    0.47
     た
    0.46
     та
    0.46
     грома
    0.46
    POSITIVE LOGITS
    comedy
    0.52
     youll
    0.44
    acoustic
    0.42
    commits
    0.42
    евич
    0.42
    CONNE
    0.41
    ARRIVAL
    0.41
    connector
    0.41
    producer
    0.40
    entertainment
    0.40
    Activations Density 0.001%

    No Known Activations