© 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. 3022
    Prev
    Next
    INDEX
    Explanations

    take and turn actions

    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
    മുണ്ട്
    0.88
    㖦
    0.84
    liked
    0.79
    䒴
    0.77
    䊂
    0.76
     पोहोच
    0.76
    梸
    0.74
     сад
    0.73
     उन्‍ह
    0.73
    㤟
    0.72
    POSITIVE LOGITS
    stile
    0.75
     turns
    0.74
    ["
    0.70
     dingin
    0.70
    ['
    0.69
     advantage
    0.68
    pike
    0.67
     nekaj
    0.64
    स्टोन
    0.64
     차
    0.64
    Activations Density 0.164%

    No Known Activations