© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5692
    Prev
    Next
    INDEX
    Explanations

    actions like funding, controlling, managing

    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
     ultraf
    1.49
     Juventus
    1.48
    <unused2213>
    1.47
    <unused2156>
    1.44
    <unused2155>
    1.44
    <unused2169>
    1.43
     fluct
    1.43
     neoliberal
    1.40
     bitcoin
    1.40
    <unused2117>
    1.39
    POSITIVE LOGITS
     사용하여
    1.08
     이용하여
    0.98
    use
    0.97
     ঘোষ
    0.93
    Application
    0.93
    Frame
    0.93
    Use
    0.92
    Sebagai
    0.91
    ini
    0.88
    经
    0.87
    Activations Density 0.000%

    No Known Activations