© 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. 84679
    Prev
    Next
    INDEX
    Explanations

    numbers and storage

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

    analogy explanations

    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
    投手
    0.47
    玷
    0.46
    迥
    0.45
    陌
    0.44
    quel
    0.43
    ثم
    0.43
    违
    0.43
    ные
    0.43
     ד
    0.42
    演绎
    0.42
    POSITIVE LOGITS
     habitats
    0.59
     government
    0.51
     bandages
    0.51
     swamps
    0.50
     abdomen
    0.49
     waist
    0.48
     sores
    0.48
     insulating
    0.47
     kerosene
    0.47
     computer
    0.47
    Activations Density 0.001%

    No Known Activations