© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 24856
    Prev
    Next
    INDEX
    Explanations

    walls on all sides

    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/layer_31_width_262k_l0_medium
    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
    ’
    0.61
     требо
    0.56
     getpath
    0.55
    .’
    0.55
    وس
    0.54
    话
    0.54
     Matteo
    0.53
    ।’
    0.53
     meyd
    0.53
     بسي
    0.52
    POSITIVE LOGITS
     wall
    1.01
     walls
    0.92
     tembok
    0.88
    Wall
    0.84
     boundary
    0.84
    壁
    0.81
     벽
    0.80
     duvar
    0.79
     Wall
    0.78
     parede
    0.76
    Activations Density 0.047%

    No Known Activations