© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 26220
    Prev
    Next
    INDEX
    Explanations

    number of bedrooms or beds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sist
    0.39
     native
    0.38
     sah
    0.38
     Couleur
    0.38
     Piper
    0.37
     Stamm
    0.36
    Piper
    0.35
     옷
    0.35
     Lent
    0.35
     Dieter
    0.35
    POSITIVE LOGITS
    Bedroom
    0.64
    bedroom
    0.63
     bedroom
    0.59
     Bedroom
    0.53
    床
    0.51
    beds
    0.50
     Bedrooms
    0.50
     bedrooms
    0.50
    bedrooms
    0.48
     床
    0.46
    Activations Density 0.001%

    No Known Activations