© 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. 226290
    Prev
    Next
    INDEX
    Explanations

    responsive

    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
    ೧
    0.46
    ільки
    0.45
    mutual
    0.42
    ォ
    0.42
    텅
    0.42
     challenged
    0.41
    숭
    0.41
    ranking
    0.41
    ientôt
    0.41
     miglia
    0.41
    POSITIVE LOGITS
     java
    0.47
    蒎
    0.43
     j
    0.43
     পরিণতি
    0.43
    ும்போது
    0.42
    规划
    0.42
     UserName
    0.41
    𝐣
    0.40
     Counc
    0.40
     তবু
    0.40
    Activations Density 0.001%

    No Known Activations