© 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. 17-GEMMASCOPE-2-RES-16K
    7. 960
    Prev
    Next
    INDEX
    Explanations

    code syntax formatting

    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_17_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
    ႆ
    0.87
    })+\
    0.86
    myfaces
    0.86
    })-\
    0.85
    ibatkan
    0.84
    }\,
    0.83
    पदी
    0.82
     pommes
    0.82
     गर्ल
    0.81
    Writer
    0.81
    POSITIVE LOGITS
    a
    1.30
    b
    1.11
     cited
    1.02
    aS
    0.96
    б
    0.94
     citado
    0.93
    p
    0.92
    ff
    0.89
     તેમજ
    0.85
     quoted
    0.78
    Activations Density 0.380%

    No Known Activations