© 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. 40387
    Prev
    Next
    INDEX
    Explanations

    to name a few

    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
    /
    -1.48
     .
    -1.47
    S
    -1.42
    thar
    -1.39
    一點
    -1.34
    {
    -1.30
    ]
    -1.30
    幾天
    -1.29
    則是
    -1.29
    何况
    -1.29
    POSITIVE LOGITS
     the
    1.57
     respald
    1.50
     there
    1.48
     regelmatig
    1.45
     jsou
    1.42
     inmiddels
    1.41
     únicamente
    1.40
     variety
    1.40
     trataba
    1.39
    hanno
    1.38
    Activations Density 0.031%

    No Known Activations