© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    long-term

    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
     factors
    0.65
     apoptosis
    0.63
     Corresponding
    0.61
     Factors
    0.60
    إ
    0.59
    ುವುದ
    0.59
    lceil
    0.59
    lfloor
    0.59
    啷
    0.58
    catenin
    0.57
    POSITIVE LOGITS
     sueño
    0.74
     loved
    0.73
    工作的
    0.72
     sense
    0.72
    既存
    0.71
    sense
    0.71
     difíciles
    0.70
     Sense
    0.70
    轉換
    0.69
    Transform
    0.69
    Activations Density 0.388%

    No Known Activations