© 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. 248137
    Prev
    Next
    INDEX
    Explanations

    we also believe / were junk

    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
    ZE
    0.56
    س
    0.52
     خان
    0.49
    ج
    0.48
    보고
    0.46
    MORDOR
    0.46
    JAK
    0.46
    غ
    0.46
    رخ
    0.46
    J
    0.45
    POSITIVE LOGITS
     praktisch
    0.48
     admitting
    0.47
     smelly
    0.46
     arrogance
    0.45
     meek
    0.45
     instinctively
    0.45
     reaffirm
    0.44
     практически
    0.44
     surfactant
    0.44
     привіт
    0.44
    Activations Density 0.001%

    No Known Activations