© 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. 9-GEMMASCOPE-2-RES-16K
    7. 1246
    Prev
    Next
    INDEX
    Explanations

    end of sentence or phrase modifiers

    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_9_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
     preferentially
    1.68
    스포츠
    1.67
     sljede
    1.62
    selectTable
    1.61
    𝗜
    1.60
    ě
    1.60
    ों
    1.59
     NSMutableArray
    1.59
    या
    1.57
    கூ
    1.56
    POSITIVE LOGITS
    on
    2.32
    ne
    1.91
    ni
    1.82
    de
    1.81
    dus
    1.81
    don
    1.81
    vät
    1.80
     $:
    1.80
    vom
    1.79
    rtle
    1.78
    Activations Density 0.090%

    No Known Activations