© 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. 177930
    Prev
    Next
    INDEX
    Explanations

    acquiring knowledge and understanding

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

    learns about important topics

    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
    ва
    0.47
    četně
    0.46
    દાર
    0.42
    方
    0.41
    Ю
    0.40
    ત્રો
    0.39
    atá
    0.39
     електро
    0.38
     JOSEPH
    0.38
    न
    0.38
    POSITIVE LOGITS
     learns
    0.61
     finds
    0.53
     aprend
    0.53
     pembelajaran
    0.52
     discovers
    0.50
     aprendizaje
    0.49
     அறிந்து
    0.49
    omania
    0.47
     aprendido
    0.46
    learn
    0.46
    Activations Density 0.001%

    No Known Activations