© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60507
    Prev
    Next
    INDEX
    Explanations

    mass and channels

    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
    ksk
    -0.72
    mergeFrom
    -0.70
    pson
    -0.67
     explí
    -0.66
     pour
    -0.66
    aktionen
    -0.66
    жник
    -0.65
    pour
    -0.65
     dezembro
    -0.64
    pose
    -0.63
    POSITIVE LOGITS
    mass
    1.04
     masses
    0.94
     mass
    0.92
    Mass
    0.88
    masses
    0.87
     Masses
    0.82
     channels
    0.82
    MASS
    0.81
     FSC
    0.78
     channel
    0.77
    Activations Density 0.061%

    No Known Activations