© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57849
    Prev
    Next
    INDEX
    Explanations

    just as concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceptar
    -0.97
     medzi
    -0.94
     ifølge
    -0.93
     pewno
    -0.90
    としては
    -0.88
    īgs
    -0.88
     între
    -0.87
    klart
    -0.86
    原始内容存档
    -0.86
    awia
    -0.86
    POSITIVE LOGITS
     simply
    6.44
     merely
    5.06
     просто
    4.84
     just
    4.84
     simplemente
    4.66
    simply
    4.53
     simplement
    4.47
    Simply
    4.09
     semplicemente
    4.03
     Simply
    3.95
    Activations Density 0.142%

    No Known Activations