© 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. 5704
    Prev
    Next
    INDEX
    Explanations

    specific historical eras and entities

    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
     saudável
    0.75
     বটে
    0.73
     लगता
    0.72
     euclidean
    0.69
     comprenant
    0.68
    लोकन
    0.66
     größer
    0.66
     ::=
    0.65
     melaksanakan
    0.65
    ικη
    0.65
    POSITIVE LOGITS
     craze
    1.03
     phenomenon
    1.03
     Movement
    1.03
     movement
    1.00
     murders
    0.97
     moniker
    0.96
     era
    0.95
     debacle
    0.93
     crisis
    0.92
     menace
    0.90
    Activations Density 0.398%

    No Known Activations