© 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. 118162
    Prev
    Next
    INDEX
    Explanations

    contractor rates, different abilities, failure INVALID

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

    offered Elara, outside her, #Israel

    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
     termed
    0.46
     reduce
    0.45
    tap
    0.44
    ano
    0.43
     synchronously
    0.43
    queue
    0.43
    🤱
    0.42
    uevo
    0.42
    allocate
    0.42
     equivalently
    0.41
    POSITIVE LOGITS
     ingenuity
    0.55
    Rustic
    0.50
    悛
    0.50
     Peggy
    0.48
     Scarlet
    0.47
    Sett
    0.46
    Scar
    0.46
     Incredible
    0.46
     Rustic
    0.46
    Iron
    0.45
    Activations Density 0.001%

    No Known Activations