© 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
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9457
    Prev
    Next
    INDEX
    Explanations

    cut off, cut through, cut back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    ت
    2.37
    an
    2.24
     Осо
    2.21
    os
    2.16
    ą
    2.09
    ेद
    2.06
    ter
    1.96
    注意的是
    1.94
     esterno
    1.93
    ेत
    1.89
    POSITIVE LOGITS
    𝗱
    2.77
    បន្ថ
    2.51
    𝗻
    2.50
    یل
    2.50
    𝗹
    2.38
    𝗴
    2.35
     swath
    2.35
     glioma
    2.30
    𝗶
    2.25
    𝑧
    2.20
    Activations Density 0.090%

    No Known Activations