© 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. 163884
    Prev
    Next
    INDEX
    Explanations

    fridges and shifts

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

    ways or longer code

    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
     ذكر
    0.47
    熾
    0.46
     devoid
    0.45
    itions
    0.45
     দেশকে
    0.44
    jections
    0.44
    Все
    0.43
     τὸ
    0.43
     rubric
    0.42
    fulfilled
    0.42
    POSITIVE LOGITS
     Ál
    0.47
    ’
    0.47
     Álvarez
    0.44
     Acre
    0.44
     sei
    0.43
     või
    0.43
     vagy
    0.42
     akşam
    0.42
     Investor
    0.42
     Controller
    0.41
    Activations Density 0.000%

    No Known Activations