© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 176376
    Prev
    Next
    INDEX
    Explanations

    covering and sealing bags

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

    persistence and duration

    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
    Negative Logits
     this
    0.42
     nikk
    0.40
     selfish
    0.40
     ¨
    0.40
     my
    0.40
     these
    0.40
    >
    0.40
     jp
    0.39
     >
    0.39
     religion
    0.38
    POSITIVE LOGITS
    𝓵
    0.46
    হৃত
    0.44
    infrared
    0.44
    electrical
    0.44
    alarm
    0.42
    temperatur
    0.42
    Interval
    0.42
    slice
    0.42
    preserved
    0.42
    𝓀
    0.42
    Activations Density 0.001%

    No Known Activations