© 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. 5963
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    陼
    0.71
     ಉದ್ದ
    0.69
     MACHINIST
    0.69
    㿝
    0.68
     placeholder
    0.67
    ...).
    0.66
    犃
    0.66
    idic
    0.66
     ধরার
    0.66
    oscopic
    0.66
    POSITIVE LOGITS
    3
    0.96
    9
    0.94
    2
    0.94
    7
    0.93
    4
    0.91
    5
    0.85
    1
    0.83
    6
    0.80
    8
    0.79
     +
    0.74
    Activations Density 0.293%

    No Known Activations