© 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. 157377
    Prev
    Next
    INDEX
    Explanations

    followed by specific terms

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

    pipeline workflow returning warm-up

    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
    שא
    0.57
    נו
    0.54
    QLabel
    0.53
    メール
    0.52
    אל
    0.51
    ミ
    0.49
    ז
    0.49
    における
    0.48
    央
    0.48
     lique
    0.48
    POSITIVE LOGITS
     ইংরে
    0.46
     Hands
    0.45
    几十
    0.45
     точно
    0.44
     пред
    0.42
     పరిస్థి
    0.41
     อะไร
    0.41
     وهذا
    0.41
     Wait
    0.40
     geht
    0.40
    Activations Density 0.000%

    No Known Activations