© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 4079
    Prev
    Next
    INDEX
    Explanations

    Autoregressive, rate limiting, precision, frigid

    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
    ั
    0.79
     Dx
    0.67
     Volume
    0.65
     DX
    0.61
    IPT
    0.60
     Bal
    0.60
     dx
    0.59
     Шо
    0.59
     Steel
    0.59
    volume
    0.59
    POSITIVE LOGITS
     coff
    0.64
     illet
    0.60
     trusting
    0.57
    ologien
    0.55
    чных
    0.55
    信
    0.55
    াত্মক
    0.55
    槿
    0.54
    stücke
    0.54
    Increasing
    0.54
    Activations Density 0.214%

    No Known Activations