© 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-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 34944
    Prev
    Next
    INDEX
    Explanations

    deviate from expectation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rivalry
    0.40
     Oxide
    0.40
    नु
    0.40
    െടുത്ത
    0.39
     ventajas
    0.39
    自動車
    0.38
    진
    0.38
    itization
    0.37
     Vorte
    0.37
    諭
    0.37
    POSITIVE LOGITS
     deviate
    0.88
     deviated
    0.84
     откло
    0.84
     deviates
    0.81
     devi
    0.78
     deviation
    0.76
     Devi
    0.75
     deviations
    0.73
    devi
    0.73
     desviación
    0.70
    Activations Density 0.010%

    No Known Activations