© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4387
    Prev
    Next
    INDEX
    Explanations

    has a

    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
     consultez
    1.84
    ARAJYA
    1.76
    認為
    1.65
     PluginResult
    1.60
     知
    1.59
    明白
    1.56
    QAry
    1.56
    TimeDict
    1.56
    了解
    1.53
     选择
    1.51
    POSITIVE LOGITS
    param
    1.12
     inherent
    1.08
     a
    0.95
    roots
    0.95
    ään
    0.94
     its
    0.93
    unga
    0.90
    ler
    0.90
    its
    0.87
    unst
    0.87
    Activations Density 0.277%

    No Known Activations