© 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. 130645
    Prev
    Next
    INDEX
    Explanations

    able to

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

    metaphors and energy

    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
    ár
    0.51
     creado
    0.47
     aport
    0.45
     legislação
    0.45
    膣
    0.45
     cilind
    0.44
    豆
    0.44
    zzles
    0.44
     sauv
    0.43
     同じ
    0.42
    POSITIVE LOGITS
     CONNE
    0.57
    CONNE
    0.50
     الكون
    0.50
    ر
    0.49
    eit
    0.49
    س
    0.49
    u
    0.47
    า
    0.47
    তিন
    0.47
    utin
    0.46
    Activations Density 0.000%

    No Known Activations