© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7746
    Prev
    Next
    INDEX
    Explanations

    Ltd

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

    programming constructs and foreign language words

    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
    лити
    0.36
    };
    0.34
    ات
    0.34
    何度
    0.34
    ”
    0.32
    ের
    0.32
    »
    0.32
    ાઓ
    0.31
    يهم
    0.31
    읊
    0.31
    POSITIVE LOGITS
     mellitus
    0.53
     الكريم
    0.50
     تعالى
    0.50
     Ltd
    0.49
    Jr
    0.49
     المبار
    0.48
    Ltd
    0.48
     تعالی
    0.47
     vulgaris
    0.46
    광역시
    0.46
    Activations Density 0.391%

    No Known Activations