© 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. 147834
    Prev
    Next
    INDEX
    Explanations

    construction and maintenance

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

    describing physical objects or actions

    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
    5
    0.63
    6
    0.59
    7
    0.53
    9
    0.51
    1
    0.50
    weak
    0.48
    0
    0.47
    Name
    0.46
    וו
    0.46
    JEE
    0.46
    POSITIVE LOGITS
     gỗ
    0.59
     paredes
    0.55
     dinding
    0.52
     toilets
    0.50
     木
    0.48
     radiators
    0.48
     Are
    0.47
     edificios
    0.47
     یور
    0.47
     walls
    0.46
    Activations Density 0.000%

    No Known Activations