© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    compliance, jurisprudence, semiconductor element

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

    functional word and subsequent word

    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_16k_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
     或者
    0.50
     akik
    0.49
    或者
    0.48
     («
    0.46
     bugün
    0.44
    bsite
    0.44
     sätt
    0.44
     或
    0.43
     amerik
    0.43
    苇
    0.41
    POSITIVE LOGITS
    Mismatch
    0.47
    etheus
    0.42
     jurisprudence
    0.40
    త్ర
    0.40
     compliance
    0.39
    やら
    0.39
    N
    0.38
     Ran
    0.38
    ERE
    0.37
    Compliance
    0.37
    Activations Density 0.021%

    No Known Activations