© 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. 78418
    Prev
    Next
    INDEX
    Explanations

    specific verbs followed by prepositions

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

    building foundations and explaining concepts

    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
    Various
    0.52
    ISupport
    0.47
    Deployment
    0.45
    নিউ
    0.45
    INCLUDING
    0.45
    간
    0.45
     ఉండ
    0.45
    待
    0.44
    Waiting
    0.44
    various
    0.44
    POSITIVE LOGITS
     spaceship
    0.51
     stopwatch
    0.50
     downloaded
    0.50
     genes
    0.49
     seventeenth
    0.48
     uang
    0.47
     shipwreck
    0.47
     sentence
    0.47
     padlock
    0.47
    rypt
    0.46
    Activations Density 0.002%

    No Known Activations