© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9104
    Prev
    Next
    INDEX
    Explanations

    code comments followed by actions

    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
     umumnya
    1.11
    »:
    1.02
     jossa
    1.01
     lehető
    1.00
    」
    1.00
    」、
    0.99
     jonka
    0.99
    »،
    0.98
     yaitu
    0.96
    ｣
    0.92
    POSITIVE LOGITS
     TODO
    1.52
    ﮑ
    1.44
    TODO
    1.40
    MARK
    1.30
     FIXME
    1.29
    solver
    1.27
    abet
    1.25
    solving
    1.25
    HERE
    1.25
    todo
    1.24
    Activations Density 0.002%

    No Known Activations