© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    sentencing and punishment

    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
    ❕
    -1.15
    ♥️
    -1.09
    Bathroom
    -1.07
     тонн
    -1.03
     οὐ
    -1.02
     chrétienne
    -1.02
    Важно
    -1.02
     rerum
    -1.00
     Acapulco
    -1.00
    円
    -1.00
    POSITIVE LOGITS
     his
    1.52
     sentence
    1.34
     punishment
    1.34
     severity
    1.31
     família
    1.26
     case
    1.26
     sentencing
    1.23
     outcome
    1.21
     treatment
    1.17
    考虑
    1.16
    Activations Density 0.048%

    No Known Activations