© 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. 206353
    Prev
    Next
    INDEX
    Explanations

    common phrases or structures

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

    even outside of

    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
    v
    0.46
     Übers
    0.45
     Sterile
    0.45
     ఉ
    0.45
    c
    0.43
    UIntValue
    0.41
     '%
    0.41
     Shampoo
    0.41
     reutil
    0.40
    ্যান
    0.40
    POSITIVE LOGITS
     sighs
    0.58
    旦
    0.52
     dents
    0.51
     রহিল
    0.50
     trovare
    0.49
    ELEASE
    0.48
     drake
    0.48
     comprendere
    0.47
     creare
    0.47
    Ფ
    0.47
    Activations Density 0.000%

    No Known Activations