© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4933
    Prev
    Next
    INDEX
    Explanations

    persecuted or minor

    np_acts-logits-general · gemini-2.5-flash-lite

    cult following or positive reassessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     många
    0.55
     nhiều
    0.48
     viele
    0.45
     mange
    0.42
     vielen
    0.41
     दशक
    0.41
     दल
    0.40
    翎
    0.40
    딕
    0.40
     many
    0.39
    POSITIVE LOGITS
     persecuted
    0.78
     persec
    0.63
     persecution
    0.59
     minor
    0.57
    MINOR
    0.54
    pers
    0.49
     Minor
    0.48
     persegu
    0.47
    Minor
    0.47
    minor
    0.46
    Activations Density 0.000%

    No Known Activations