© 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. 172
    Prev
    Next
    INDEX
    Explanations

    how many, how long, how much

    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
    有两种
    0.92
     있어서
    0.84
     पड़ने
    0.83
     whichever
    0.77
     هناك
    0.77
    基础上
    0.74
    的基础上
    0.73
    ⩾
    0.73
    There
    0.72
    whatever
    0.71
    POSITIVE LOGITS
     much
    1.74
     far
    1.45
    much
    1.41
     many
    1.35
     Much
    1.34
    Much
    1.31
     mucho
    1.26
     does
    1.22
     muchos
    1.21
     muitos
    1.15
    Activations Density 1.060%

    No Known Activations