© 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. 22-GEMMASCOPE-RES-131K
    7. 15659
    Prev
    Next
    INDEX
    Explanations

    tall buildings and towers

    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_22/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
     about
    -1.09
    šno
    -1.08
    onek
    -1.03
    ToShow
    -1.02
     egos
    -0.99
    باع
    -0.93
    ລ
    -0.92
    skapet
    -0.91
     التهاب
    -0.91
     needed
    -0.90
    POSITIVE LOGITS
     building
    1.43
     buildings
    1.34
     edificio
    1.29
    Building
    1.13
     flotte
    1.12
     housing
    1.09
     Building
    1.09
     BUILDING
    1.04
    building
    1.02
     suspendu
    1.02
    Activations Density 0.044%

    No Known Activations