© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16902
    Prev
    Next
    INDEX
    Explanations

    units and steps

    np_acts-logits-general · gemini-2.5-flash-lite

    std::endl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .$.
    0.43
    ⁢</
    0.41
    向けの
    0.40
    იდან
    0.39
    ോട്ടോ
    0.39
     टेक्स्ट
    0.38
    Playlist
    0.38
    titor
    0.38
    жнее
    0.38
    ষ্টিত
    0.38
    POSITIVE LOGITS
    iar
    0.43
    <0xB9>
    0.41
    }^{
    0.41
    kept
    0.41
    }^{-}
    0.41
    }^{\
    0.40
    IA
    0.39
    II
    0.39
    }^{*
    0.38
     placed
    0.38
    Activations Density 0.001%

    No Known Activations