© 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. 169826
    Prev
    Next
    INDEX
    Explanations

    phrases linked by common follow-up words

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

    Banking, Minecraft, client

    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
    ו
    0.61
    ла
    0.57
    على
    0.51
    המ
    0.51
    י
    0.49
    ടി
    0.47
    აში
    0.46
    वर्धन
    0.46
     आयर
    0.46
     Andaman
    0.45
    POSITIVE LOGITS
    りと
    0.44
    รายละเอียด
    0.44
    drinks
    0.43
     drinks
    0.43
     grossly
    0.42
     is
    0.41
    afin
    0.41
    aily
    0.41
     Least
    0.41
    念
    0.41
    Activations Density 0.001%

    No Known Activations