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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46513
    Prev
    Next
    INDEX
    Explanations

    political happenings

    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
     χρησιμοποι
    0.47
     Просто
    0.45
     ई
    0.44
     มัน
    0.44
     utilized
    0.42
     Euler
    0.42
     чыныгы
    0.42
     útil
    0.42
     它
    0.41
     множество
    0.41
    POSITIVE LOGITS
     political
    0.50
     politico
    0.49
    political
    0.48
     happenings
    0.48
    政治
    0.46
     blackmail
    0.45
     traumas
    0.45
     jornalista
    0.44
     політи
    0.44
     homosexuality
    0.43
    Activations Density 0.002%

    No Known Activations