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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118751
    Prev
    Next
    INDEX
    Explanations

    copyrights and scripts

    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
    xyl
    -0.88
    glBegin
    -0.83
    ">"
    -0.75
    子が
    -0.74
     """
    
    -0.73
    lent
    -0.73
    uggle
    -0.72
    offsetHeight
    -0.72
     spannend
    -0.71
    Nominations
    -0.71
    POSITIVE LOGITS
     étro
    0.89
     broader
    0.79
    ͎
    0.79
    Months
    0.76
     потім
    0.75
     Waiver
    0.73
    atki
    0.70
     kellett
    0.69
     months
    0.69
    PACE
    0.67
    Activations Density 0.002%

    No Known Activations