© 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. 8464
    Prev
    Next
    INDEX
    Explanations

    corresponding angles and equivalents

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

    equivalent input counterparts

    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
     আশা
    0.40
     Bedford
    0.38
     бесплатно
    0.38
     உதவு
    0.38
     ചൂ
    0.37
    抡
    0.37
     ሁሉም
    0.37
     रामबा
    0.37
     ঝ
    0.37
     помогают
    0.36
    POSITIVE LOGITS
     counterparts
    0.57
     equivalent
    0.52
     corresponding
    0.52
     equivalents
    0.50
     equivalente
    0.49
     counterpart
    0.44
    equivalent
    0.44
     corresponded
    0.43
     corresponds
    0.42
     correspondences
    0.42
    Activations Density 0.000%

    No Known Activations