© 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. 147942
    Prev
    Next
    INDEX
    Explanations

    fluid kingdom, giants

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

    questions, tasks, and specific items

    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
     Services
    0.48
     Contr
    0.47
      
    0.46
    ↵↵
    0.46
    ஏ
    0.46
     Todo
    0.46
     Name
    0.46
    ↵
    0.45
     retorn
    0.45
     The
    0.45
    POSITIVE LOGITS
    inio
    0.59
    ফু
    0.58
    सेवी
    0.55
    뎃
    0.54
    as
    0.52
    ings
    0.51
    et
    0.50
    rot
    0.50
    rocyte
    0.50
    van
    0.48
    Activations Density 0.000%

    No Known Activations