Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2929
    Prev
    Next
    INDEX
    Explanations

    what are

    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
    ity
    0.69
     égard
    0.66
     surtout
    0.65
    呀
    0.65
    umination
    0.64
    ention
    0.62
    呢
    0.62
     yeah
    0.62
    せ
    0.59
    MB
    0.59
    POSITIVE LOGITS
     possible
    1.16
     some
    1.14
     возможных
    1.08
     몇
    1.08
     algunos
    1.07
     algunas
    1.04
     mögliche
    1.03
     beberapa
    1.02
     Possible
    1.02
     semua
    1.01
    Activations Density 0.274%

    No Known Activations