© 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. 34-GEMMASCOPE-RES-131K
    7. 99098
    Prev
    Next
    INDEX
    Explanations

    legal charges and convictions

    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
     letto
    -0.98
     mingled
    -0.87
     treasured
    -0.84
    ábamos
    -0.82
     électron
    -0.80
    ᅱ
    -0.80
    
    -0.80
     mutiara
    -0.79
    stolen
    -0.79
     asesinato
    -0.79
    POSITIVE LOGITS
     sentenced
    2.34
     charged
    1.86
     ordered
    1.61
     convicted
    1.51
     found
    1.40
    charged
    1.32
     fined
    1.29
     indicted
    1.14
     awarded
    1.14
     charge
    1.14
    Activations Density 0.044%

    No Known Activations