© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 40
    Prev
    Next
    INDEX
    Explanations

    amount or degree

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

    quantity or degree

    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_53_width_65k_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
     quelconque
    0.23
     теркәлүсез
    0.23
     最大
    0.23
    othed
    0.21
     några
    0.21
    ській
    0.21
     /{
    0.20
     sommige
    0.20
     replete
    0.20
     [`
    0.20
    POSITIVE LOGITS
     firepower
    0.56
     leeway
    0.53
     flexibility
    0.50
     headroom
    0.50
     mileage
    0.49
     variability
    0.48
     emphasis
    0.48
     excitement
    0.48
     fanfare
    0.48
     attention
    0.46
    Activations Density 0.917%

    No Known Activations