© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209931
    Prev
    Next
    INDEX
    Explanations

    sentence end"

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

    identifying specific parts or characteristics

    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_31_width_262k_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
    ాత్ర
    0.47
    呿
    0.47
    নীতিক
    0.46
    ై
    0.45
     odst
    0.45
     rilas
    0.44
    ában
    0.44
    傗
    0.43
    ниці
    0.43
     Investing
    0.42
    POSITIVE LOGITS
     first
    0.52
     kelompok
    0.50
     granular
    0.47
     आशा
    0.47
    schol
    0.46
    avis
    0.45
     Lega
    0.45
     in
    0.44
     terrace
    0.43
     chuan
    0.43
    Activations Density 0.001%

    No Known Activations