© 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. 22-GEMMASCOPE-RES-131K
    7. 129197
    Prev
    Next
    INDEX
    Explanations

    starts of descriptive phrases

    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
     they
    -0.99
    destroyAll
    -0.96
    他們
    -0.96
    
    -0.96
    եռ
    -0.95
    They
    -0.93
    快速的
    -0.91
     februar
    -0.90
    反应过来
    -0.90
     mať
    -0.89
    POSITIVE LOGITS
    ]
    0.88
    }]);
    0.87
    forgot
    0.85
    жения
    0.84
    ➢
    0.81
     ruido
    0.80
    友情
    0.79
     interessanti
    0.79
    ется
    0.76
     нега
    0.76
    Activations Density 0.000%

    No Known Activations