© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    enclosed spaces or structures

    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_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
     sociis
    2.16
     demikian
    2.11
    зка
    2.06
    ları
    2.06
    ़
    2.01
     placebo
    1.99
    нали
    1.92
    𝙏
    1.91
     perte
    1.83
    urte
    1.80
    POSITIVE LOGITS
    क
    3.14
    e
    2.86
    ↻
    2.78
    or
    2.69
    ي
    2.54
    es
    2.49
    i
    2.47
    sdf
    2.43
    u
    2.43
    {
    2.41
    Activations Density 0.006%

    No Known Activations