© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117760
    Prev
    Next
    INDEX
    Explanations

    criticism and legal issues

    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_34/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
     diamant
    -1.00
    沏
    -0.98
     Tense
    -0.94
     сахара
    -0.89
     violations
    -0.86
     raffin
    -0.84
    ü
    -0.84
     vege
    -0.84
    तः
    -0.81
    mais
    -0.81
    POSITIVE LOGITS
     robust
    1.08
    ajaan
    1.00
     both
    0.98
    ॰
    0.98
     highlighting
    0.92
     facilitating
    0.91
    khó
    0.91
    sack
    0.90
     ContentValues
    0.89
     }));
    0.88
    Activations Density 0.052%

    No Known Activations