© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181482
    Prev
    Next
    INDEX
    Explanations

    language words

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

    created, built, express, frying

    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_31_width_262k_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
    䧼
    0.60
    峀
    0.55
    িপি
    0.54
    从业
    0.53
     규
    0.52
     валю
    0.51
     îl
    0.51
    倠
    0.50
     consecutively
    0.49
     expertly
    0.49
    POSITIVE LOGITS
     bonita
    0.53
     manchas
    0.53
    Mais
    0.49
     meninas
    0.49
     more
    0.48
     Mais
    0.48
     mais
    0.47
     más
    0.46
     zapatos
    0.46
    mais
    0.46
    Activations Density 0.001%

    No Known Activations