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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 12767
    Prev
    Next
    INDEX
    Explanations

    dependency and permission declarations

    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
    ب
    1.36
    ی
    1.29
    νά
    1.27
    xlabel
    1.21
    те
    1.21
    omena
    1.20
    ków
    1.19
    e
    1.19
    anız
    1.19
    uv
    1.17
    POSITIVE LOGITS
     SST
    1.24
    𝙍
    1.21
     unscathed
    1.18
     curtailed
    1.16
     immig
    1.16
    Ско
    1.16
     fortifications
    1.14
     makeshift
    1.14
    startX
    1.13
     Refugees
    1.13
    Activations Density 0.005%

    No Known Activations