© 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. 101055
    Prev
    Next
    INDEX
    Explanations

    legally, literary, infidelity, generating, I, being, create, photography, performer

    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
     org
    0.52
     that
    0.50
     Political
    0.47
     "
    0.46
     Social
    0.46
     علی
    0.45
     la
    0.45
     ja
    0.45
     Culture
    0.45
     of
    0.44
    POSITIVE LOGITS
    loé
    0.61
    ρης
    0.52
    𒅆
    0.50
    pleo
    0.49
    ása
    0.47
    enciais
    0.47
    لې
    0.45
     publiée
    0.45
    ڙ
    0.45
    隰
    0.44
    Activations Density 0.001%

    No Known Activations