© 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. 63692
    Prev
    Next
    INDEX
    Explanations

    public constructor declarations

    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
     participaron
    -0.93
    vierung
    -0.90
    contained
    -0.88
    쩌
    -0.85
     zwłaszcza
    -0.81
    IMHO
    -0.81
    
    -0.80
    Açık
    -0.79
    不容易
    -0.79
    ramiento
    -0.79
    POSITIVE LOGITS
    public
    1.88
    constructor
    1.48
     public
    1.38
     constructor
    1.30
     will
    1.12
     Constructor
    1.12
    构造
    1.08
     无
    1.06
     构造
    0.94
    Constructors
    0.92
    Activations Density 0.028%

    No Known Activations