© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and physics concepts

    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
    MinIntensity
    1.47
     CentOS
    1.45
    ፴
    1.43
     intolerable
    1.42
     nDims
    1.39
     disinfection
    1.38
     deaktiv
    1.38
     perpetrated
    1.37
     refusing
    1.36
    <0x11>
    1.34
    POSITIVE LOGITS
    en
    1.64
    ↵
    1.47
    on
    1.46
    l
    1.41
     medal
    1.36
    zelfde
    1.36
    ol
    1.30
    a
    1.27
    s
    1.27
    e
    1.27
    Activations Density 0.097%

    No Known Activations