© 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. 19586
    Prev
    Next
    INDEX
    Explanations

    past tense auxiliaries

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

    modal verb phrases

    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
     изображения
    0.51
    Ϝ
    0.50
    Neurons
    0.48
    Acknowledg
    0.48
    MovementControls
    0.48
     மூட
    0.48
     लाखों
    0.47
     புரா
    0.47
    Ꮷ
    0.46
     பிரபலமான
    0.45
    POSITIVE LOGITS
     علاج
    0.42
     apologise
    0.42
     Laurent
    0.40
     وعد
    0.39
     advises
    0.38
    itié
    0.38
     servizio
    0.38
     sjuk
    0.38
     préstamo
    0.38
     поез
    0.37
    Activations Density 0.022%

    No Known Activations