© 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. 58769
    Prev
    Next
    INDEX
    Explanations

    past participles after verbs

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

    list introductions, labels, or separators

    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
     maneuvers
    0.54
     implements
    0.52
     borrows
    0.51
     repairs
    0.51
     ")");
    0.49
     isset
    0.49
     adjectives
    0.48
     demonstrates
    0.47
     identifies
    0.47
     neuron
    0.47
    POSITIVE LOGITS
     विवेक
    0.55
    डे
    0.54
     продолжа
    0.47
    यू
    0.45
    س
    0.45
    cau
    0.44
    cant
    0.44
    Asie
    0.44
    there
    0.42
     सर्क
    0.42
    Activations Density 0.000%

    No Known Activations