© 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. 23155
    Prev
    Next
    INDEX
    Explanations

    numbers and common words followed by specific outcomes

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

    steps in a process

    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
     ','
    0.44
    竑
    0.42
    ு
    0.41
    コ
    0.41
     设计
    0.41
    局部
    0.40
    窣
    0.40
     چ
    0.40
    人形
    0.39
     அழக
    0.38
    POSITIVE LOGITS
    နိုင်
    0.49
    🫶
    0.46
     totaling
    0.46
     emocionante
    0.45
     шанс
    0.44
    accessed
    0.44
     अर्जित
    0.44
    獲得
    0.43
     graciously
    0.42
     raffle
    0.42
    Activations Density 0.000%

    No Known Activations