© 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. 8347
    Prev
    Next
    INDEX
    Explanations

    Angular and related technologies

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

    basic angular

    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
    シア
    0.43
     इकट
    0.42
    槇
    0.42
    🫶
    0.42
     നെറ്റ്‌വർ
    0.40
    韌
    0.39
    🥹
    0.39
    ChatGPT
    0.37
    🫡
    0.37
    宗教
    0.36
    POSITIVE LOGITS
     Angular
    1.65
     angular
    1.59
    Angular
    1.55
     ng
    1.47
    angular
    1.44
     Ng
    1.36
     ngOnInit
    1.35
    rxjs
    1.33
    ngx
    1.28
     rxjs
    1.27
    Activations Density 0.008%

    No Known Activations