© 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. 1055
    Prev
    Next
    INDEX
    Explanations

    turn off

    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
     Athe
    0.53
    啟
    0.52
     turno
    0.50
    瓣
    0.49
    abcdef
    0.47
     Funds
    0.47
     Gap
    0.47
     باکس
    0.47
     @
    0.47
    @
    0.47
    POSITIVE LOGITS
    Mak
    0.68
     eigene
    0.62
     crawls
    0.59
    igraph
    0.59
     Morin
    0.59
     circ
    0.59
     circulate
    0.59
     recirculation
    0.58
     उर्वशी
    0.58
     show
    0.58
    Activations Density 0.903%

    No Known Activations