© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59453
    Prev
    Next
    INDEX
    Explanations

    volume or quantity

    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
    一枚
    -0.79
    Tuition
    -0.77
    尽
    -0.76
     père
    -0.72
    会上
    -0.70
    ינוך
    -0.69
     createState
    -0.69
     trí
    -0.68
     doInBackground
    -0.68
    錦
    -0.68
    POSITIVE LOGITS
     volume
    6.38
    volume
    5.34
     volumes
    5.16
    Volume
    4.81
     Volume
    4.66
     VOLUME
    4.28
    VOLUME
    4.03
     Volumes
    4.03
    volumes
    3.95
     volumen
    3.83
    Activations Density 0.079%

    No Known Activations