© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 162
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ர்ப
    0.72
     طلعت
    0.68
     Rachael
    0.65
    ств
    0.65
    icore
    0.61
    ProfileAction
    0.60
     रेश
    0.59
    ဠ
    0.59
     قيمه
    0.58
    ர்க்க
    0.58
    POSITIVE LOGITS
     year
    2.94
    year
    2.58
     Year
    2.47
     years
    2.44
    Year
    2.39
     YEAR
    2.24
     año
    2.20
    years
    2.13
    YEAR
    2.08
     Years
    2.02
    Activations Density 2.728%

    No Known Activations