© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 759
    Prev
    Next
    INDEX
    Explanations

    Hello World

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    <unused2113>
    0.60
     mumkin
    0.58
     우리의
    0.58
    嚟
    0.58
     problémy
    0.58
    <unused2140>
    0.56
    檤
    0.55
     elég
    0.55
     nahin
    0.55
     consommation
    0.55
    POSITIVE LOGITS
    ♠
    0.64
    🎫
    0.63
    ♣
    0.63
    <0xF0>
    0.56
    💹
    0.55
    ☎
    0.54
    🎮
    0.53
    ✖
    0.53
    🏦
    0.53
    🛠
    0.52
    Activations Density 0.011%

    No Known Activations