© 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. 22-GEMMASCOPE-RES-131K
    7. 33548
    Prev
    Next
    INDEX
    Explanations

    another instance of

    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_22/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
    そのため
    -1.18
     first
    -1.00
     before
    -0.97
     различ
    -0.94
     erste
    -0.94
    estión
    -0.92
     amid
    -0.88
     ersten
    -0.86
     incoming
    -0.85
     Behörden
    -0.85
    POSITIVE LOGITS
     another
    1.73
    今度は
    1.59
     szint
    1.55
     again
    1.54
    ibid
    1.54
     ebenfalls
    1.51
    nother
    1.48
    อีก
    1.42
    también
    1.39
     similarly
    1.38
    Activations Density 0.050%

    No Known Activations