© 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. 78198
    Prev
    Next
    INDEX
    Explanations

    code, math, and tags

    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
     radically
    -0.84
    ﷲ
    -0.80
    וֹ
    -0.80
     آنها
    -0.79
    Does
    -0.79
    芾
    -0.78
    ulisan
    -0.77
    HostException
    -0.76
    omalies
    -0.74
    Chord
    -0.74
    POSITIVE LOGITS
     '\
    1.02
     !=
    0.86
    anInt
    0.83
    ints
    0.82
     method
    0.81
    鸚
    0.81
     Furniture
    0.80
    𝛾
    0.80
     государства
    0.80
     праздни
    0.80
    Activations Density 0.000%

    No Known Activations