© 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. 203204
    Prev
    Next
    INDEX
    Explanations

    brittleness and robustness

    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
    稠
    0.44
     integrantes
    0.44
     intellectuals
    0.44
     ਦ
    0.42
    兩種
    0.42
    ים
    0.42
     ע
    0.41
     அறு
    0.41
     ਸ
    0.41
    𝗯
    0.41
    POSITIVE LOGITS
    Cooper
    0.50
    Drama
    0.46
    Passenger
    0.45
    Kelly
    0.45
    纽约
    0.45
    Laura
    0.44
    Actress
    0.44
    Editor
    0.43
    Updated
    0.42
    Penalty
    0.42
    Activations Density 0.006%

    No Known Activations