© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    beans or history

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

    irrelevant, wheezing

    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
     muß
    1.05
     skall
    0.97
     daß
    0.81
     marvellous
    0.81
    部份
    0.79
     !!!!!
    0.74
    :-)
    0.73
     mempunyai
    0.72
     причем
    0.71
     !!!!
    0.70
    POSITIVE LOGITS
    ––
    0.91
     —
    0.88
    ⁠
    0.87
    ⏤
    0.84
     kiddos
    0.84
     ー
    0.80
     reimag
    0.79
    —
    0.79
    —”
    0.75
     проєкту
    0.75
    Activations Density 0.826%

    No Known Activations