© 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. 216216
    Prev
    Next
    INDEX
    Explanations

    end for new, the sensor

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

    systems outside, dedicated to, store state, monsoon arrives, alerts

    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
     super
    0.47
     SAP
    0.46
     sap
    0.46
     sna
    0.46
     gc
    0.45
     further
    0.45
     য
    0.45
     को
    0.45
     fissures
    0.44
     فره
    0.44
    POSITIVE LOGITS
    past
    0.52
    habilit
    0.51
    ttl
    0.50
    wild
    0.48
    다음
    0.48
    riek
    0.47
    Equation
    0.47
    solve
    0.47
    menu
    0.46
    regar
    0.46
    Activations Density 0.000%

    No Known Activations