© 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
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 2863
    Prev
    Next
    INDEX
    Explanations

    gentle physical touch

    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
    DVR
    0.71
    izoph
    0.69
     hoops
    0.69
     eBay
    0.69
     postan
    0.68
     Wagon
    0.68
     avatars
    0.68
    鳃
    0.67
     DVR
    0.67
     hém
    0.67
    POSITIVE LOGITS
     touch
    1.04
     stroke
    0.95
     touching
    0.94
     touches
    0.88
    touch
    0.87
     strokes
    0.87
    TOUCH
    0.80
     Touch
    0.80
    タッチ
    0.79
     stroked
    0.79
    Activations Density 0.234%

    No Known Activations