© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7042
    Prev
    Next
    INDEX
    Explanations

    Latin endings like ase, ade, ose

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

    Paseo, redeploy, paneer, omelet, caveats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    OW
    0.39
    ولی
    0.38
     กําลัง
    0.38
     считаю
    0.37
     இவற்ற
    0.37
    lars
    0.37
    शोर
    0.36
    ℅
    0.36
    仼
    0.36
     corporate
    0.35
    POSITIVE LOGITS
    cki
    0.62
    ña
    0.57
    ño
    0.57
    ffect
    0.55
    aux
    0.54
    ř
    0.54
    ceği
    0.53
    ckiego
    0.52
    ños
    0.51
    czki
    0.51
    Activations Density 0.076%

    No Known Activations