© 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. 1241
    Prev
    Next
    INDEX
    Explanations

    deeply complex or personal

    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
    is
    3.00
    礴
    2.93
     beneficios
    2.73
    SdkVersion
    2.72
     conveyors
    2.60
    hanti
    2.49
     feats
    2.48
    ാതെ
    2.47
     annoy
    2.45
     cottages
    2.41
    POSITIVE LOGITS
    в
    2.93
    де
    2.81
    ם
    2.80
    د
    2.73
    rafa
    2.47
     độ
    2.40
     druh
    2.37
     betrachtet
    2.37
     sampai
    2.37
    ਚ
    2.36
    Activations Density 0.944%

    No Known Activations