© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6624
    Prev
    Next
    INDEX
    Explanations

    common preceding words and following distinct terms

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

    shoe sore, Ponzi, light, experimental

    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
    蛋糕
    0.41
     разными
    0.40
     разных
    0.39
    饼
    0.37
    吣
    0.37
    źnie
    0.36
    蛋
    0.36
    鸡蛋
    0.36
     Palms
    0.35
     pâle
    0.35
    POSITIVE LOGITS
     soaking
    0.46
     spar
    0.45
     imbib
    0.42
     Soak
    0.41
     CSP
    0.40
     nutr
    0.40
    ád
    0.40
     deix
    0.39
     pf
    0.39
     prefix
    0.39
    Activations Density 0.000%

    No Known Activations