© 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. 53-GEMMASCOPE-2-RES-262K
    7. 37481
    Prev
    Next
    INDEX
    Explanations

    CVE identifiers

    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/layer_53_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
    <sup>
    0.44
     January
    0.38
     janvier
    0.38
    )}-
    0.37
     أبريل
    0.37
    GDP
    0.37
     января
    0.36
     मार्च
    0.36
    歲
    0.36
    year
    0.36
    POSITIVE LOGITS
    كله
    0.39
     lütfen
    0.38
    ட்ர
    0.38
    ម្បី
    0.38
    Photon
    0.38
    Sometimes
    0.37
     karakter
    0.37
     മനുഷ്യ
    0.37
    व्यक्त
    0.36
     herzlich
    0.36
    Activations Density 0.004%

    No Known Activations