© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3628
    Prev
    Next
    INDEX
    Explanations

    political ideologies and groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
    borne
    1.01
    geschoss
    0.84
     Shay
    0.83
    makarna
    0.82
    chief
    0.81
    犊
    0.80
    ائنات
    0.79
    ानंतर
    0.79
     Okada
    0.78
     département
    0.77
    POSITIVE LOGITS
    ism
    1.35
    isme
    1.05
    ISM
    1.01
    ismo
    1.00
    ismus
    0.93
    ismos
    0.83
    isms
    0.81
    鹼
    0.72
    aster
    0.70
    ским
    0.69
    Activations Density 0.289%

    No Known Activations