© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1995
    Prev
    Next
    INDEX
    Explanations

    environments and to build

    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
     timid
    0.66
    веро
    0.61
     fickle
    0.59
     infrequent
    0.59
     css
    0.58
    胆
    0.57
     ఇటీ
    0.56
     aching
    0.55
    询
    0.54
     Bulletin
    0.53
    POSITIVE LOGITS
     forests
    1.32
     forest
    1.26
     rainforest
    1.22
     jungle
    1.16
     Forest
    1.13
     caves
    1.10
     palace
    1.10
     oceans
    1.10
     Forests
    1.10
     skyscrapers
    1.09
    Activations Density 0.769%

    No Known Activations