© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 122704
    Prev
    Next
    INDEX
    Explanations

    hurricane Irma

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

    Ukraine independence

    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
    Not in Any Lists

    No Comments

    Negative Logits
    m
    0.50
    b
    0.50
    chair
    0.48
    v
    0.48
    놀
    0.47
     poiché
    0.47
    ບ
    0.47
    os
    0.46
     necesitaba
    0.46
    ém
    0.46
    POSITIVE LOGITS
     Zeta
    0.54
     Zebra
    0.50
     EZ
    0.47
     LiDAR
    0.47
     ZTE
    0.47
     Рэ
    0.47
     Gauge
    0.47
     سود
    0.45
    統一
    0.45
     Wide
    0.44
    Activations Density 0.000%

    No Known Activations