© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10381
    Prev
    Next
    INDEX
    Explanations

    severe harm and serious consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     ロ
    1.58
     หรือ
    1.53
     Alternatively
    1.49
     Although
    1.47
    หรือ
    1.46
    または
    1.46
     atau
    1.46
    Alternatively
    1.45
    Although
    1.45
     nebo
    1.44
    POSITIVE LOGITS
    架构
    1.15
     tenets
    1.15
    닮
    1.14
     factored
    1.07
     axioms
    1.07
     닮
    1.06
     visage
    1.06
     intrinsic
    1.05
     insuring
    1.04
     structuring
    1.04
    Activations Density 0.293%

    No Known Activations