© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10270
    Prev
    Next
    INDEX
    Explanations

    Explainable

    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_22_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
     Query
    1.00
     રો
    1.00
    yser
    0.98
    ့
    0.92
    ubs
    0.92
     buzzing
    0.91
    指數
    0.91
    ның
    0.89
    蠔
    0.88
     cult
    0.87
    POSITIVE LOGITS
    ellas
    1.02
    gorod
    0.99
     footsteps
    0.93
     scom
    0.91
    inite
    0.90
    iembre
    0.90
    nina
    0.89
    Configs
    0.89
    itates
    0.86
    ena
    0.86
    Activations Density 0.009%

    No Known Activations