© 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. 4195
    Prev
    Next
    INDEX
    Explanations

    direct address terms

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

    terms of endearment

    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
     Patients
    0.39
     Quadrup
    0.38
    他和
    0.36
    
    0.36
    ottes
    0.35
     Subjects
    0.35
    ઈએ
    0.35
    켠
    0.34
    حياته
    0.34
    学生的
    0.33
    POSITIVE LOGITS
     sir
    1.48
     dude
    1.37
     dear
    1.34
     buddy
    1.30
     amigo
    1.23
     guys
    1.21
     brother
    1.20
     darling
    1.17
     querido
    1.16
     bro
    1.15
    Activations Density 0.269%

    No Known Activations