© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    held

    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
     sympathies
    0.65
     Universal
    0.61
     River
    0.61
     paisley
    0.60
     साक्षी
    0.59
     randomNumber
    0.58
     Referral
    0.58
    勧
    0.58
    怀疑
    0.57
     추천
    0.57
    POSITIVE LOGITS
     held
    1.14
     holding
    1.13
     hold
    1.10
    held
    1.09
     holds
    1.00
     Holding
    0.97
     Hold
    0.97
    holding
    0.96
    Holding
    0.95
     Held
    0.94
    Activations Density 0.299%

    No Known Activations