© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15507
    Prev
    Next
    INDEX
    Explanations

    Autom pages Ver Stream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     messed
    1.17
     wrongdoing
    1.15
     conspired
    1.12
     hombres
    1.05
    дил
    1.05
     mastermind
    1.05
    屣
    1.01
     адам
    0.99
     endangering
    0.99
     misery
    0.98
    POSITIVE LOGITS
    Ver
    1.03
    Z
    1.01
    Li
    0.97
     Ver
    0.93
    Core
    0.90
    nano
    0.90
    Stream
    0.88
    Cultural
    0.86
     Z
    0.86
    Star
    0.86
    Activations Density 0.089%

    No Known Activations