© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5827
    Prev
    Next
    INDEX
    Explanations

    religious figures and historical narratives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    цер
    0.83
     சித்தர்
    0.80
     cappuccino
    0.77
     neur
    0.74
    贛
    0.72
     Brem
    0.71
     ಶ್ರೀ
    0.70
     Capp
    0.70
     інте
    0.70
     Wheeling
    0.70
    POSITIVE LOGITS
     Aaron
    0.83
    Aaron
    0.80
     nation
    0.78
     Joshua
    0.76
     Pharaoh
    0.76
     national
    0.74
    蟻
    0.73
     Nation
    0.73
     Trojans
    0.73
     israel
    0.71
    Activations Density 0.092%

    No Known Activations