© 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. 5131
    Prev
    Next
    INDEX
    Explanations

    sky and stars

    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
     molasses
    0.75
     জীবনী
    0.75
    informat
    0.70
     Bahasa
    0.70
     Remix
    0.70
     piecewise
    0.70
    巧克力
    0.70
    杖
    0.69
     xen
    0.68
     chocolate
    0.67
    POSITIVE LOGITS
     sky
    1.43
    Sky
    1.19
     Sky
    1.15
    sky
    1.12
     skies
    1.11
     cielo
    1.05
     heavens
    1.00
     SKY
    0.98
     céu
    0.98
     starg
    0.96
    Activations Density 0.219%

    No Known Activations