© 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. 130106
    Prev
    Next
    INDEX
    Explanations

    contrast and transition

    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
     "");
    -1.44
     specially
    -1.42
     nordrhein
    -1.41
    satunya
    -1.38
    ější
    -1.34
    不可能
    -1.33
    ämme
    -1.33
    इटम
    -1.33
    حيث
    -1.32
     possibly
    -1.31
    POSITIVE LOGITS
    .
    1.91
    饜
    1.46
    is
    1.40
    ta
    1.38
    relenting
    1.37
     don
    1.35
    私に
    1.34
     incluidos
    1.30
            
    1.30
     imó
    1.29
    Activations Density 0.005%

    No Known Activations