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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 859
    Prev
    Next
    INDEX
    Explanations

    initial letters followed by specific acronyms

    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_29_width_262k_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
    <unused2161>
    0.35
    Przypisy
    0.33
    <unused2181>
    0.32
    enegro
    0.32
    Dens
    0.31
    <unused2130>
    0.31
    Buch
    0.30
    L
    0.30
    R
    0.30
    Ez
    0.30
    POSITIVE LOGITS
    ailing
    0.28
    GI
    0.27
    ITE
    0.27
    GC
    0.27
    aving
    0.27
    aking
    0.27
    IVE
    0.26
    ôle
    0.26
    eyer
    0.26
    VC
    0.26
    Activations Density 0.431%

    No Known Activations