© 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. 30088
    Prev
    Next
    INDEX
    Explanations

    completing objectives

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

    gameplay and objectives

    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
     혹은
    0.45
    もしくは
    0.44
    ▢
    0.43
    quera
    0.42
    🧔
    0.42
    텃
    0.42
     beispielsweise
    0.41
    
    0.41
    であれば
    0.40
     darse
    0.40
    POSITIVE LOGITS
     गुना
    0.47
    Id
    0.46
    రీలు
    0.45
     bans
    0.45
     machines
    0.45
    DeviceId
    0.44
    PostMapping
    0.44
    ups
    0.44
     kilow
    0.44
     मशी
    0.43
    Activations Density 0.000%

    No Known Activations