© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 2202
    Prev
    Next
    INDEX
    Explanations

    darkness, shadows, silence

    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
    ী
    1.44
    股
    1.31
     uts
    1.30
    手的
    1.26
     humane
    1.20
    isimple
    1.20
    नेल
    1.19
     Ea
    1.19
     Wasch
    1.18
     uređ
    1.18
    POSITIVE LOGITS
     obscurity
    2.06
    obsc
    1.98
     obsc
    1.72
     ciem
    1.59
     shadows
    1.59
     darkness
    1.59
    茫
    1.55
     recesses
    1.51
    Opacity
    1.51
     curtain
    1.50
    Activations Density 0.653%

    No Known Activations