© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205753
    Prev
    Next
    INDEX
    Explanations

    subjective opinion

    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
    Negative Logits
    mutable
    0.47
     исполнения
    0.46
     unlike
    0.45
    These
    0.44
     recognising
    0.44
    these
    0.42
    Unlike
    0.42
     испол
    0.40
     these
    0.40
    艦
    0.40
    POSITIVE LOGITS
    Ư
    0.61
    รียน
    0.49
    ឈ្មោះ
    0.44
    佲
    0.43
     ਵ
    0.43
    ett
    0.43
     周
    0.43
     tuổi
    0.43
     hoera
    0.43
    entukan
    0.42
    Activations Density 0.008%

    No Known Activations