© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 63126
    Prev
    Next
    INDEX
    Explanations

    wavy lines hanging down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     Umwelt
    0.42
     विज्ञ
    0.42
     Öncelikle
    0.40
    IVACON
    0.40
    iesel
    0.38
    ꯡ
    0.37
     बैंकिंग
    0.37
     (\%)
    0.36
    籁
    0.36
    癞
    0.36
    POSITIVE LOGITS
    this
    0.42
    furniture
    0.41
    created
    0.40
     erecting
    0.38
    Vac
    0.38
    khan
    0.37
    conclusion
    0.36
    alors
    0.36
    vac
    0.35
    void
    0.35
    Activations Density 0.026%

    No Known Activations