© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18006
    Prev
    Next
    INDEX
    Explanations

    but and contrastive statements

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

    but and contrast statements

    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
     waarbij
    0.32
    بيرة
    0.30
    printStackTrace
    0.29
     lesquelles
    0.28
    Խ
    0.28
    ፁ
    0.28
    Ꮮ
    0.28
    िश्व
    0.28
    찝
    0.28
    socketList
    0.27
    POSITIVE LOGITS
     it
    0.48
     это
    0.38
     there
    0.37
     It
    0.36
     הוא
    0.35
     they
    0.35
     Isaiah
    0.35
     nobody
    0.34
     niemand
    0.34
     यह
    0.34
    Activations Density 0.180%

    No Known Activations