© 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. 10-GEMMASCOPE-RES-131K
    7. 100149
    Prev
    Next
    INDEX
    Explanations

    the number two

    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_10/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
    .
    -1.59
     to
    -1.50
     new
    -1.44
    енча
    -1.43
     same
    -1.42
     of
    -1.38
     further
    -1.38
     gleiche
    -1.38
     Verhältnis
    -1.34
    ↵↵
    -1.27
    POSITIVE LOGITS
     hao
    1.54
     who
    1.45
    却没有
    1.44
    <bos>
    1.43
    »,
    1.39
    以上です
    1.38
     keo
    1.38
     하고
    1.37
    俩
    1.34
    じゃん
    1.33
    Activations Density 0.105%

    No Known Activations