© 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. 90242
    Prev
    Next
    INDEX
    Explanations

    periodic, numbers, space, issues

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

    tracing protocols, vanished groups

    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
    B
    0.55
    checkbox
    0.52
    C
    0.47
    L
    0.47
    了一个
    0.45
    Thy
    0.45
    Away
    0.44
     قائد
    0.44
    V
    0.44
    observer
    0.44
    POSITIVE LOGITS
     menggunakan
    0.51
     becomes
    0.51
     theologians
    0.50
     kurulum
    0.50
     ribu
    0.48
     alt
    0.46
     olmad
    0.46
     uses
    0.45
     kurul
    0.45
     alternates
    0.45
    Activations Density 0.000%

    No Known Activations