© 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. 2785
    Prev
    Next
    INDEX
    Explanations

    Harmful

    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
    vät
    0.61
    vian
    0.57
     murderers
    0.57
    濃度
    0.56
    Mon
    0.56
    牍
    0.56
    聚合
    0.55
    蚯
    0.55
    芸
    0.54
     Summ
    0.54
    POSITIVE LOGITS
     rå
    0.69
     hi
    0.64
     ഉപ
    0.61
     asesor
    0.61
     imp
    0.61
     consejos
    0.59
     hangers
    0.57
    回避
    0.56
    raint
    0.56
     সত
    0.56
    Activations Density 0.264%

    No Known Activations