© 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. 29898
    Prev
    Next
    INDEX
    Explanations

    his/him's

    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
     wer
    0.42
     closures
    0.39
    自行
    0.38
     lossless
    0.37
    ⇆
    0.37
    bees
    0.37
     couples
    0.37
    令人
    0.36
     darkness
    0.35
    式
    0.35
    POSITIVE LOGITS
     him
    1.08
     그의
    1.07
     அவரை
    1.07
     honom
    1.07
     তাকে
    1.02
     jego
    1.02
     его
    0.99
    彼の
    0.94
     అతని
    0.92
    把他
    0.92
    Activations Density 0.167%

    No Known Activations