© 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
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 1051
    Prev
    Next
    INDEX
    Explanations

    helpful and harmless purpose

    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
     camadas
    0.57
     catches
    0.57
     econometric
    0.56
     cracking
    0.56
     पंतप्रधान
    0.56
    ⌒
    0.56
     شامل
    0.55
     locking
    0.54
     odont
    0.53
    unordered
    0.53
    POSITIVE LOGITS
    ಬ
    0.65
    Confirm
    0.61
     confirmed
    0.59
     Confirm
    0.58
     সিদ্ধান্ত
    0.55
     Boat
    0.54
    лями
    0.53
     સુ
    0.53
     Opera
    0.53
     décider
    0.52
    Activations Density 1.239%

    No Known Activations