© 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. 135124
    Prev
    Next
    INDEX
    Explanations

    Kardashian family

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

    inputs, nucleus, processing

    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
     benefic
    0.47
    ophagy
    0.41
     clasp
    0.41
    CTest
    0.41
     absur
    0.40
     verbally
    0.40
     /ˈ
    0.40
     fistule
    0.40
     verbal
    0.39
     língua
    0.39
    POSITIVE LOGITS
     enterprising
    0.46
    少了
    0.44
    াড়াও
    0.44
    ্ি
    0.43
     COLLISIONS
    0.43
    另外
    0.42
    ীদ
    0.42
    revenue
    0.42
    àng
    0.41
    执
    0.41
    Activations Density 0.002%

    No Known Activations