© 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. 24281
    Prev
    Next
    INDEX
    Explanations

    calendar, Congress, students, preservation

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

    describing attributes or components

    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
     पली
    0.47
    ిన
    0.46
    Suc
    0.46
    icing
    0.45
    entially
    0.45
    𝙘
    0.43
     논
    0.43
     Suc
    0.43
    ాలు
    0.42
    icies
    0.42
    POSITIVE LOGITS
    
    0.51
    ஞ்ஞான
    0.50
    bieter
    0.47
     seam
    0.46
    precise
    0.45
     klimat
    0.45
     reducir
    0.45
    snippet
    0.45
    縫
    0.45
     peroxide
    0.44
    Activations Density 0.000%

    No Known Activations