© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79003
    Prev
    Next
    INDEX
    Explanations

    noun followed by a preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.22
    そして
    -1.09
    なぜ
    -0.92
    <bos>
    -0.86
    และ
    -0.86
    および
    -0.85
    また
    -0.84
    生態
    -0.82
    以及
    -0.82
    があり
    -0.81
    POSITIVE LOGITS
    ごとの
    1.02
    為に
    1.02
    の基本
    0.96
    浓郁
    0.94
    Então
    0.92
    感じが
    0.92
    改为
    0.91
    事を
    0.89
    事です
    0.89
    ssymb
    0.88
    Activations Density 0.207%

    No Known Activations