© 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. 48214
    Prev
    Next
    INDEX
    Explanations

    possibility, alternative, or condition

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

    probability of "or"

    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
    0.53
    頂いた
    0.48
     downtown
    0.45
     User
    0.44
     diving
    0.44
    業
    0.44
     Chron
    0.43
    <0xE3>
    0.43
     outstanding
    0.43
     Engineering
    0.42
    POSITIVE LOGITS
    或者
    0.57
     或者
    0.48
     অথবা
    0.47
    禟
    0.45
     reacciones
    0.45
    spiracy
    0.44
     खबरों
    0.44
     可能
    0.44
    rimi
    0.43
     нельзя
    0.43
    Activations Density 0.000%

    No Known Activations