© 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. 1308
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
     நூற்ற
    0.68
    啪
    0.68
    findBy
    0.67
    sunami
    0.64
    ances
    0.63
    ríamos
    0.63
     pelos
    0.62
    ॉम
    0.61
    awing
    0.61
    埓
    0.61
    POSITIVE LOGITS
     concentrating
    0.84
     exclusively
    0.82
     intently
    0.81
     inward
    0.81
    grouped
    0.79
     attention
    0.79
    oriented
    0.78
    Emphasis
    0.78
     Attention
    0.78
     centred
    0.77
    Activations Density 0.387%

    No Known Activations