© 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. 22-GEMMASCOPE-RES-131K
    7. 129707
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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_22/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
     builtin
    -0.99
     GME
    -0.96
     presidenta
    -0.92
     قوان
    -0.90
     severa
    -0.90
    もありました
    -0.89
    怼
    -0.88
    Tracce
    -0.85
     bastion
    -0.85
     البيانات
    -0.84
    POSITIVE LOGITS
     klient
    0.90
     Nasional
    0.89
     passés
    0.88
    没
    0.87
    ]',
    0.85
     sklo
    0.85
     ekolog
    0.85
    })),
    0.84
     ulo
    0.84
     afectado
    0.84
    Activations Density 0.045%

    No Known Activations