© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3809
    Prev
    Next
    INDEX
    Explanations

    seeking purpose or context

    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_17_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
    wallepics
    1.14
     introvert
    1.14
    <unused763>
    1.11
    Ⲁ
    1.10
     Sp
    1.09
    瑢
    1.08
    @[+][
    1.07
    <unused986>
    1.06
    ىر
    1.05
    𒆝
    1.05
    POSITIVE LOGITS
    0.81
    .
    0.68
    &
    0.63
    ・
    0.59
    /
    0.59
    s
    0.57
    的目的
    0.56
    from
    0.54
    3
    0.54
     circled
    0.52
    Activations Density 0.033%

    No Known Activations