© 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. 85260
    Prev
    Next
    INDEX
    Explanations

    sequences of events

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

    Ancient Egypt, worker counts, pose a risk

    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
     directe
    0.59
    ¹.
    0.54
     direkte
    0.54
     مستقیم
    0.53
     beton
    0.51
     reimag
    0.51
    assanam
    0.50
     doğrudan
    0.50
     paradigma
    0.49
    尓
    0.49
    POSITIVE LOGITS
    scenario
    0.44
    license
    0.44
     કે
    0.42
    logic
    0.42
    sequences
    0.42
    processing
    0.40
    },
    0.40
    clock
    0.40
     సిని
    0.40
    series
    0.40
    Activations Density 0.002%

    No Known Activations