© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2907
    Prev
    Next
    INDEX
    Explanations

    на

    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
    や
    -0.84
    komme
    -0.82
    湾
    -0.82
     Proust
    -0.81
    勇者
    -0.79
    な
    -0.79
    中心
    -0.78
    allowNull
    -0.77
    дыду
    -0.76
     akti
    -0.75
    POSITIVE LOGITS
    турой
    1.16
    steroids
    0.88
     ועל
    0.83
    截图
    0.81
     occasion
    0.80
     behalf
    0.79
     until
    0.77
     throughout
    0.77
     Throughout
    0.76
     meningkat
    0.75
    Activations Density 0.011%

    No Known Activations