© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2814
    Prev
    Next
    INDEX
    Explanations

    review

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags enthusiastic references to polar wildlife—especially penguins and polar bears—in a TV/discovery‐style context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ؛
    0.98
     multidis
    0.96
    さまざまな
    0.92
    ；
    0.91
     terdapat
    0.88
     необхідно
    0.86
     және
    0.85
     meghatá
    0.84
     exhilar
    0.82
    
    0.82
    POSITIVE LOGITS
     crappy
    1.70
     shitty
    1.63
    ってる
    1.62
     fucking
    1.56
     merda
    1.54
     lmao
    1.49
     bullshit
    1.48
    してる
    1.48
     asshole
    1.44
     idiots
    1.43
    Activations Density 1.283%

    No Known Activations