© 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. 31-GEMMASCOPE-2-RES-262K
    7. 139156
    Prev
    Next
    INDEX
    Explanations

    political goals

    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_31_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
    鈦
    0.52
     его
    0.50
    钛
    0.50
     рас
    0.48
     لما
    0.47
    פא
    0.47
    ել
    0.46
     соба
    0.46
    лом
    0.45
     симво
    0.45
    POSITIVE LOGITS
     nights
    0.46
     –
    0.45
     strolled
    0.45
     network
    0.44
     pathway
    0.44
     yards
    0.44
     gradient
    0.43
     progenitors
    0.43
    até
    0.43
     adults
    0.43
    Activations Density 0.006%

    No Known Activations