© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10747
    Prev
    Next
    INDEX
    Explanations

    look closely

    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
     It
    -2.36
     If
    -2.11
     to
    -1.92
     There
    -1.64
     Such
    -1.59
     on
    -1.54
     since
    -1.48
     Thus
    -1.48
     After
    -1.46
     Hoping
    -1.45
    POSITIVE LOGITS
    ⾞
    1.85
     ウィメンズ
    1.81
    ︕
    1.66
    釹
    1.65
    ᅚ
    1.59
    檍
    1.58
     několik
    1.52
     セットアップ
    1.52
     撮っ
    1.52
    ();
    1.50
    Activations Density 0.022%

    No Known Activations