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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82284
    Prev
    Next
    INDEX
    Explanations

    academic integrity

    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
     Credential
    -0.83
     poussière
    -0.82
     captives
    -0.82
     lawful
    -0.81
     Criticism
    -0.81
    Αν
    -0.76
     Defects
    -0.76
     ignores
    -0.76
     Critics
    -0.74
     چرم
    -0.73
    POSITIVE LOGITS
     cheating
    2.81
     cheat
    2.30
     cheated
    2.09
     cheats
    1.94
    cheat
    1.77
    Cheat
    1.63
     Cheat
    1.59
     dishonest
    1.52
     Che
    1.51
     honesty
    1.41
    Activations Density 0.010%

    No Known Activations