© 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. 588
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by specific continuations

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

    influences

    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
    gz
    0.19
    <0x0D>
    0.18
     হইলে
    0.18
     Config
    0.18
    ăz
    0.17
     Bits
    0.17
     &&
    0.17
    _
    0.17
    btn
    0.17
    員
    0.17
    POSITIVE LOGITS
     shores
    0.22
     suburbs
    0.22
     skies
    0.21
     suburb
    0.21
     spreading
    0.21
     tantamount
    0.21
     Watertown
    0.20
     plummet
    0.20
     recoup
    0.20
     proper
    0.20
    Activations Density 0.510%

    No Known Activations