© 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. 179954
    Prev
    Next
    INDEX
    Explanations

    giving out

    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
    édez
    0.44
    ますが
    0.43
    rema
    0.40
    atthakath
    0.40
     apertura
    0.39
    ΩΝ
    0.39
    branchNode
    0.39
    ၍
    0.39
    స్తు
    0.38
     میشود
    0.38
    POSITIVE LOGITS
    ắt
    0.46
    நாயக
    0.45
    Russian
    0.43
    ピオン
    0.42
    रेशन
    0.41
    ποίηση
    0.41
    公子
    0.40
     fern
    0.40
    லய
    0.40
     enslaved
    0.40
    Activations Density 0.001%

    No Known Activations