© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60622
    Prev
    Next
    INDEX
    Explanations

    rooms, doors, and fittings

    np_acts-logits-general · gemini-2.5-flash-lite

    house features and outdoor spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    histoire
    0.55
     postseason
    0.48
     postdoc
    0.46
    ǎng
    0.41
    Histoire
    0.41
    ্লাস
    0.40
     สง
    0.39
    ]));
    0.39
    Movies
    0.39
     upcoming
    0.39
    POSITIVE LOGITS
    adihi
    0.42
     polypropylene
    0.40
    بعض
    0.40
     erine
    0.40
     některé
    0.39
    енера
    0.39
     కాల
    0.39
     verschiedene
    0.38
     acetic
    0.38
     eri
    0.38
    Activations Density 0.017%

    No Known Activations