© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133717
    Prev
    Next
    INDEX
    Explanations

    reading image data

    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_40_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
     movimientos
    0.41
     interpret
    0.41
     fama
    0.40
     idem
    0.40
     jet
    0.39
     mobility
    0.39
    非
    0.39
     nullptr
    0.38
     sama
    0.38
     facelift
    0.38
    POSITIVE LOGITS
    antown
    0.40
    樊
    0.40
    वश
    0.39
    ㄗ
    0.39
    chließlich
    0.39
    铭
    0.39
    憔
    0.39
     clutching
    0.38
     colorful
    0.38
     așa
    0.37
    Activations Density 0.000%

    No Known Activations