© 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. 799
    Prev
    Next
    INDEX
    Explanations

    key items and overviews

    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
    <unused100>
    0.25
    <unused2130>
    0.25
    <unused2138>
    0.23
    \%).
    0.22
    <unused2164>
    0.22
    <unused2121>
    0.21
    <unused2222>
    0.21
     zehn
    0.21
    issaient
    0.21
    <unused2120>
    0.20
    POSITIVE LOGITS
     |
    0.49
     &
    0.44
    :
    0.43
     -
    0.40
     –
    0.40
     =
    0.39
     +
    0.38
     vs
    0.37
     Overview
    0.36
     Explained
    0.36
    Activations Density 2.728%

    No Known Activations