© 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. 13-GEMMASCOPE-2-RES-16K
    4. 9931
    Prev
    Next
    INDEX
    Explanations

    what have we here

    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_13_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
     keep
    0.95
     Keep
    0.87
     بالط
    0.85
     Keeping
    0.84
     keeping
    0.83
     الأكثر
    0.80
    ంగు
    0.79
    纂
    0.75
    iavelli
    0.74
    مكان
    0.73
    POSITIVE LOGITS
    tested
    1.15
    sexual
    1.12
    ৃত্য
    1.10
    ismic
    1.08
     lymph
    1.08
    lymph
    1.06
    behav
    1.05
    weapon
    1.05
     sentencing
    1.04
    washed
    1.04
    Activations Density 0.000%

    No Known Activations