© 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. 258183
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Celebr
    0.51
     cenário
    0.46
    лега
    0.45
    加坡
    0.45
     seizoen
    0.45
    姚
    0.44
     Celebr
    0.44
    ipelago
    0.44
     മുതൽ
    0.44
    водства
    0.43
    POSITIVE LOGITS
    物質
    0.43
    つ
    0.43
    に入れて
    0.43
     smrti
    0.42
     kasnije
    0.42
    x
    0.42
    mx
    0.41
    蟻
    0.41
    n
    0.40
     معروف
    0.40
    Activations Density 0.001%

    No Known Activations