© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48082
    Prev
    Next
    INDEX
    Explanations

    myspace

    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
    https
    -0.81
    ݣ
    -0.79
    ⁠
    -0.78
     unaff
    -0.78
     Brexit
    -0.78
    patu
    -0.77
    affiliation
    -0.74
    \\\
    -0.73
     affiliated
    -0.73
    Mar
    -0.73
    POSITIVE LOGITS
                
    1.02
    ��������
    0.97
     MySpace
    0.90
    腟
    0.77
    <h1>
    0.76
    myspace
    0.76
     bloody
    0.75
     Vitro
    0.73
     enlarged
    0.73
     Varan
    0.72
    Activations Density 0.040%

    No Known Activations