© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2574
    Prev
    Next
    INDEX
    Explanations

    recycled, recruitment, recurrent

    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_7_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
    rowData
    2.87
    थमिक
    2.65
     शर्त
    2.62
    𝔀
    2.51
    当たり
    2.50
    +#+#
    2.50
    Fluid
    2.42
    érico
    2.41
     vencedor
    2.39
    𝚆
    2.38
    POSITIVE LOGITS
    წყვე
    3.24
     파
    2.77
    rone
    2.75
    r
    2.74
    ன்கள்
    2.62
    dic
    2.62
    ivered
    2.57
    dur
    2.56
    dür
    2.50
    moved
    2.48
    Activations Density 0.059%

    No Known Activations