© 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. 186414
    Prev
    Next
    INDEX
    Explanations

    a category or type opener

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

    numbers and specific terms

    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
    toxicity
    0.51
    ﮑ
    0.50
    Rag
    0.49
    ﺤ
    0.49
     počas
    0.49
    plating
    0.48
    Cohen
    0.48
    दरअसल
    0.48
    ﺒ
    0.48
    ುಂಬ
    0.47
    POSITIVE LOGITS
     happens
    0.43
     consists
    0.42
    块
    0.42
    อี
    0.41
     వెంట
    0.40
    ))(
    0.40
    最短
    0.40
    ような
    0.39
    ))=\
    0.39
    わけで
    0.38
    Activations Density 0.001%

    No Known Activations