© 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. 8466
    Prev
    Next
    INDEX
    Explanations

    when it

    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
     위해
    0.42
     щоб
    0.40
     그럼
    0.38
     ว่า
    0.38
     ไ
    0.37
    )
    0.37
     注意
    0.36
     เพ
    0.36
     MTLTexture
    0.35
    ०
    0.35
    POSITIVE LOGITS
    soever
    0.66
     it
    0.63
     confronted
    0.54
     faced
    0.51
     there
    0.50
     considering
    0.50
     you
    0.47
    ce
    0.46
     asked
    0.46
     they
    0.46
    Activations Density 0.029%

    No Known Activations