© 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. 3539
    Prev
    Next
    INDEX
    Explanations

    what's on your mind

    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
     বিস্মিত
    0.83
     resear
    0.75
    UnifiedTopology
    0.75
    ႃ
    0.75
    OUTH
    0.75
    ଥ
    0.74
    VhZ
    0.73
     dearly
    0.73
    __":
    0.73
     Tanık
    0.72
    POSITIVE LOGITS
     something
    0.85
    Something
    0.75
     Something
    0.74
    something
    0.70
     Что
    0.69
     cualquiera
    0.68
     Tack
    0.64
     cosas
    0.63
     someth
    0.63
     Fácil
    0.62
    Activations Density 0.098%

    No Known Activations