© 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. 112537
    Prev
    Next
    INDEX
    Explanations

    assigning blame or fault

    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
     If
    -1.82
     although
    -1.59
     this
    -1.55
     despite
    -1.55
    (
    -1.53
     indifferent
    -1.50
     albeit
    -1.47
    </i>
    -1.47
     если
    -1.45
    Although
    -1.45
    POSITIVE LOGITS
    iſter
    1.54
    ↵
    1.52
     आइटम
    1.50
    觊
    1.48
    why
    1.48
     remplacé
    1.47
     confirmación
    1.44
     pérd
    1.44
     combinatie
    1.41
     następnie
    1.41
    Activations Density 0.017%

    No Known Activations