© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    la. la- HeDB SNR

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

    case variations of 'a'

    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
    ంబేద్కర్
    0.41
    रोला
    0.35
    <unused28>
    0.35
    ⸨
    0.35
    Khokhlov
    0.34
    ຂໍ້ມ
    0.33
    ⎆
    0.33
    ल्डेन
    0.33
    ۇل
    0.33
    Ꮸ
    0.33
    POSITIVE LOGITS
     i
    0.56
    0.55
     )
    0.54
     l
    0.52
     .
    0.52
     ;
    0.52
     d
    0.50
     °
    0.50
     x
    0.49
     t
    0.49
    Activations Density 0.362%

    No Known Activations