© 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. 251592
    Prev
    Next
    INDEX
    Explanations

    shall be

    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
     각각
    0.52
     láp
    0.49
    𝐰
    0.46
     potranno
    0.46
     암
    0.45
     importants
    0.45
    iffent
    0.44
    分别
    0.43
     위한
    0.43
    Therates
    0.43
    POSITIVE LOGITS
     Because
    0.43
    มากกว่า
    0.42
    袢
    0.42
    Because
    0.41
    Reilly
    0.39
     Sunday
    0.39
    поро
    0.39
     workaround
    0.38
    Tram
    0.38
     frameborder
    0.38
    Activations Density 0.001%

    No Known Activations