© 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. 30569
    Prev
    Next
    INDEX
    Explanations

    underfloor heating

    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
    ousse
    -0.80
     kf
    -0.74
    vaila
    -0.73
     enx
    -0.73
     Fritz
    -0.73
    בים
    -0.71
    ateria
    -0.70
    oblig
    -0.69
    ENES
    -0.69
    ferences
    -0.69
    POSITIVE LOGITS
     radiant
    1.98
     floor
    1.77
    floor
    1.55
     Floor
    1.48
    Radiant
    1.46
     inflo
    1.42
     Radiant
    1.39
     floors
    1.37
    Floor
    1.28
     under
    1.25
    Activations Density 0.014%

    No Known Activations