© 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. 34-GEMMASCOPE-RES-131K
    7. 3249
    Prev
    Next
    INDEX
    Explanations

    process and thread states

    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
     görev
    -0.78
     节
    -0.69
    companyname
    -0.67
    żna
    -0.65
    RESEARCH
    -0.65
    世界
    -0.65
    Claro
    -0.65
     nonostante
    -0.65
    Translations
    -0.64
    PMID
    -0.64
    POSITIVE LOGITS
     ready
    1.26
     PCB
    1.06
     running
    0.99
     Ready
    0.96
     Running
    0.94
     sleep
    0.94
     quanto
    0.92
     pcb
    0.91
    ready
    0.89
     processo
    0.88
    Activations Density 0.008%

    No Known Activations