© 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. 212094
    Prev
    Next
    INDEX
    Explanations

    when followed by past tense

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

    neutralizing, expansion, creations, python, vibrate, complexities

    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
    ING
    0.59
     युवाओ
    0.46
     менедже
    0.44
     হলিউ
    0.43
    NFL
    0.43
     スタッドレス
    0.42
    客
    0.42
    _=
    0.41
    Sn
    0.40
     ESTATE
    0.40
    POSITIVE LOGITS
     نیز
    0.48
     befol
    0.48
    য়ন
    0.47
     refroid
    0.46
     möglicherweise
    0.46
     también
    0.46
    andria
    0.46
    ينا
    0.45
     paus
    0.44
     ativar
    0.43
    Activations Density 0.000%

    No Known Activations