© 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. 9535
    Prev
    Next
    INDEX
    Explanations

    doorways and access

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

    doors and gates

    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
    ي
    0.59
    കളെ
    0.55
    ين
    0.54
     qué
    0.53
     unterstützen
    0.52
     allem
    0.51
     größte
    0.51
     rene
    0.50
     kapital
    0.49
     garis
    0.48
    POSITIVE LOGITS
    🚪
    1.42
    Doors
    1.23
     Doors
    1.21
     दरवाजा
    1.21
    doors
    1.20
    ドア
    1.20
    门
    1.20
     doors
    1.16
     Door
    1.16
     двери
    1.16
    Activations Density 0.102%

    No Known Activations