© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7827
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
     esperti
    1.09
     aucun
    1.08
    ペイ
    1.02
    ğun
    1.01
    众
    1.01
    hört
    0.99
     исторических
    0.97
    眾
    0.97
     الإلكتر
    0.97
    Educational
    0.96
    POSITIVE LOGITS
    ိန်
    0.99
     IMO
    0.95
     IMHO
    0.95
     Ehe
    0.95
    חוז
    0.94
     нынеш
    0.92
     aforementioned
    0.90
     GeoNames
    0.89
    ນີ້
    0.89
    င်္ဂ
    0.88
    Activations Density 0.008%

    No Known Activations