© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    high or similar words

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

    high and highest

    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
    colspan
    0.36
    ಪು
    0.34
    儩
    0.34
    笤
    0.33
    uszt
    0.33
     simpler
    0.32
    گون
    0.31
     فونی
    0.31
    이브
    0.31
    قلال
    0.31
    POSITIVE LOGITS
     high
    4.69
    high
    4.53
     yüksek
    4.06
    高
    4.00
    High
    3.88
     vysok
    3.84
     उच्च
    3.83
     גבוה
    3.78
     wysok
    3.75
    HIGH
    3.73
    Activations Density 1.113%

    No Known Activations