© 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. 102596
    Prev
    Next
    INDEX
    Explanations

    lower scores

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

    potential instability

    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
     diper
    0.52
    teri
    0.48
    掃
    0.48
    uri
    0.48
     lin
    0.46
    тере
    0.45
    timezone
    0.45
     memper
    0.45
     pendek
    0.44
    τζ
    0.44
    POSITIVE LOGITS
     আটক
    0.51
    ج
    0.48
    ش
    0.46
    ólicos
    0.46
     adhesions
    0.45
     उन्हीं
    0.45
     incubating
    0.45
     imprisonment
    0.44
     droughts
    0.44
     ecosystems
    0.44
    Activations Density 0.001%

    No Known Activations