© 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. 126760
    Prev
    Next
    INDEX
    Explanations

    disciplines, training, applying to positions

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

    specific entities and their connections

    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
    Sobre
    0.43
    ExtensionsPath
    0.42
    ilmiştir
    0.42
    月
    0.41
    մ
    0.41
     সঞ্চ
    0.41
    physik
    0.41
    虚
    0.41
    踹
    0.41
    Overlay
    0.40
    POSITIVE LOGITS
     newspap
    0.53
     Glove
    0.52
     participan
    0.51
     televiz
    0.49
     Connie
    0.48
     courteous
    0.47
     Cont
    0.46
     दोबारा
    0.46
     spectrogram
    0.45
     cenu
    0.45
    Activations Density 0.001%

    No Known Activations