© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129416
    Prev
    Next
    INDEX
    Explanations

    common word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite

    illusion of closenessfundamental building blocksleading zeros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝓼
    0.50
     পি
    0.49
     kamb
    0.48
     с
    0.47
     বোর্ডের
    0.47
     கம்ப
    0.47
    män
    0.47
     เด่น
    0.47
     馬
    0.47
     פ
    0.46
    POSITIVE LOGITS
    Effects
    0.49
     efectos
    0.45
     enfermedad
    0.42
     Effects
    0.40
    累计
    0.40
    だけでも
    0.39
    ]
    0.39
    Along
    0.39
     afe
    0.39
    用い
    0.39
    Activations Density 0.000%

    No Known Activations