© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    is there anything

    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
     β
    0.61
     ста
    0.60
     incapable
    0.60
     गाडी
    0.59
     Automobile
    0.59
    ८
    0.59
    عو
    0.58
    عی
    0.58
     silico
    0.57
     предвари
    0.57
    POSITIVE LOGITS
    forever
    0.75
    是一家
    0.71
     Soon
    0.70
     schlim
    0.68
     sicher
    0.67
    기는
    0.67
     Dlatego
    0.67
    Soon
    0.66
    isak
    0.66
    很好
    0.65
    Activations Density 0.033%

    No Known Activations