© 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. 17952
    Prev
    Next
    INDEX
    Explanations

    policy, offerings, previous, money

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

    Outlays

    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
    Ջ
    0.43
    楇
    0.41
    ローマ
    0.39
     "\
    0.39
     vody
    0.39
     সঙ্গে
    0.38
    缺乏
    0.38
     fluidity
    0.38
    विला
    0.38
    䏹
    0.38
    POSITIVE LOGITS
    slick
    0.39
     Linn
    0.37
    gggg
    0.37
    sg
    0.37
    snippets
    0.36
     Utilities
    0.36
    sgd
    0.36
    layers
    0.36
    居然
    0.35
    抑
    0.35
    Activations Density 0.000%

    No Known Activations