© 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. 223604
    Prev
    Next
    INDEX
    Explanations

    unique ancient traditions

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

    code, operations, or lists

    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
     লো
    0.53
     Together
    0.47
     bouillon
    0.45
    lymph
    0.44
     taxonomic
    0.43
     kilo
    0.43
    s
    0.42
    lo
    0.42
    processing
    0.42
    submitted
    0.42
    POSITIVE LOGITS
    नियर
    0.46
    intérieur
    0.46
    ላለ
    0.46
    ɺ
    0.45
     closeModal
    0.45
     живота
    0.44
    काउंट
    0.44
     анти
    0.43
    ທ
    0.43
     перехода
    0.42
    Activations Density 0.001%

    No Known Activations