© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7062
    Prev
    Next
    INDEX
    Explanations

    `pd`, `json`, `math`

    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
     Wider
    0.50
     širo
    0.47
     wider
    0.42
    wider
    0.40
    一定的
    0.39
     champagne
    0.39
    ≲
    0.39
    広く
    0.38
     elusive
    0.38
    ‌്
    0.38
    POSITIVE LOGITS
    ListIterator
    0.47
    regex
    0.41
    だよ
    0.38
    UUID
    0.38
    )(
    0.37
    ")(
    0.37
    ObjectId
    0.36
    빡
    0.36
    plex
    0.36
    yloxy
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.