© 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. 5795
    Prev
    Next
    INDEX
    Explanations

    turn out screws

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

    Model Systems

    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
     russo
    0.52
    危機
    0.51
    俄罗斯
    0.50
     санк
    0.49
     ხელისუფ
    0.48
     რუს
    0.47
     Russland
    0.47
    俄
    0.46
    利益
    0.46
     России
    0.45
    POSITIVE LOGITS
     longitudinal
    0.59
     Longitudinal
    0.52
     tubercles
    0.51
     longitudinale
    0.50
     longitudinally
    0.49
     transverse
    0.49
     brushes
    0.48
     previamente
    0.48
     notches
    0.48
     obliquely
    0.48
    Activations Density 0.043%

    No Known Activations