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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 848
    Prev
    Next
    INDEX
    Explanations

    catching exceptions

    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
    iteli
    1.79
     MODKEY
    1.52
    ulata
    1.44
    indole
    1.43
    asih
    1.43
    <unused275>
    1.43
    하게
    1.42
    ivg
    1.40
    iteten
    1.39
     하지
    1.38
    POSITIVE LOGITS
     famously
    1.42
     Clearly
    1.19
     «
    1.16
     Tuttavia
    1.14
     cialis
    1.13
     ActiveRecord
    1.12
     ‘‘
    1.12
     Confront
    1.11
     Obama
    1.10
     billionaire
    1.07
    Activations Density 0.816%

    No Known Activations