© 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. 24280
    Prev
    Next
    INDEX
    Explanations

    Credit to

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

    equal citizenship

    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
    慰
    0.47
     गईं
    0.42
     lotus
    0.42
    🍬
    0.41
     выражения
    0.41
    见过
    0.40
    または
    0.40
    にならない
    0.40
    )</
    0.40
     jaye
    0.40
    POSITIVE LOGITS
     Hungarian
    0.57
     Argentine
    0.53
     Legends
    0.50
     Πα
    0.49
     acar
    0.49
     Brazilian
    0.48
    ，
    0.48
     Argentina
    0.47
     Laboratory
    0.47
     Titans
    0.46
    Activations Density 0.000%

    No Known Activations