© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    organization names and their contexts

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

    technical / procedural phrases

    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
    袅
    0.44
     Vols
    0.41
    طات
    0.41
    𒉺
    0.40
    㑨
    0.40
     páginas
    0.39
     ప్రి
    0.39
     चित्रों
    0.39
    鏤
    0.39
    جلات
    0.38
    POSITIVE LOGITS
    ană
    0.36
    ana
    0.35
    </em>
    0.34
    ike
    0.33
    he
    0.33
    backslash
    0.33
    imon
    0.32
    ʌ
    0.32
    hana
    0.32
    anna
    0.31
    Activations Density 0.292%

    No Known Activations