© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 220
    Prev
    Next
    INDEX
    Explanations

    ad, landing page, report ID

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

    odd numbers and identifiers

    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
    IRCONIUM
    0.35
    疖
    0.35
    physiological
    0.34
    OLYBDENUM
    0.34
    embryon
    0.33
    irradiated
    0.32
    URNIZOR
    0.32
    aqueous
    0.32
    Lycodon
    0.32
    Hydrochloride
    0.32
    POSITIVE LOGITS
    _
    0.43
     payments
    0.36
     taxes
    0.35
     payment
    0.35
     market
    0.34
     revenue
    0.34
     info
    0.33
    ↵
    0.33
     data
    0.33
     login
    0.33
    Activations Density 0.035%

    No Known Activations