© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137447
    Prev
    Next
    INDEX
    Explanations

    Titanic sinking and wreck

    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
    </u>
    0.41
     pilas
    0.39
    Mayor
    0.38
    NavigationView
    0.38
     গোলে
    0.38
    נט
    0.38
    看到
    0.37
    ^\
    0.37
    bas
    0.36
     dura
    0.36
    POSITIVE LOGITS
    粦
    0.47
    衾
    0.45
     Eurostile
    0.44
    可通过
    0.43
    chodzi
    0.43
     inquire
    0.42
    ówki
    0.42
     परिचय
    0.41
    仕様
    0.41
    HasFieldError
    0.41
    Activations Density 0.009%

    No Known Activations