© 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. 200684
    Prev
    Next
    INDEX
    Explanations

    foreign language elements

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

    semantically relevant

    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
    \
    0.50
     Controller
    0.44
    ழிப்பு
    0.44
     Voice
    0.44
     "~
    0.40
     alterar
    0.40
     indicar
    0.40
    $}
    0.40
    خاب
    0.39
     controller
    0.39
    POSITIVE LOGITS
    েলি
    0.53
    éléments
    0.52
     እንዲሁ
    0.52
     stubborn
    0.51
    ouverture
    0.51
     উপাদান
    0.51
     եւ
    0.51
     germinate
    0.51
     கடுமையான
    0.50
     распространен
    0.49
    Activations Density 0.001%

    No Known Activations