© 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-65K
    7. 6455
    Prev
    Next
    INDEX
    Explanations

    harm and repetition

    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_65k_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
    だけど
    0.46
    இந்திய
    0.46
    B
    0.44
    ஹ
    0.44
     निवड
    0.43
    Berikut
    0.43
    ۔
    0.42
    ។
    0.42
    এখানে
    0.42
    pictured
    0.41
    POSITIVE LOGITS
     underlies
    0.68
     constitutes
    0.67
     exemplifies
    0.64
     provides
    0.63
     represents
    0.62
     has
    0.59
     serves
    0.59
     poses
    0.59
     merupakan
    0.59
     является
    0.59
    Activations Density 0.001%

    No Known Activations