© 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. 41-GEMMASCOPE-2-RES-262K
    7. 35169
    Prev
    Next
    INDEX
    Explanations

    Stateful, Persistent, PVC, money, store, getter

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    haber
    0.41
    redux
    0.39
    Reg
    0.39
    icz
    0.39
    Superhero
    0.38
    mem
    0.38
    Sigma
    0.38
    æt
    0.38
    alp
    0.37
    芨
    0.37
    POSITIVE LOGITS
     getter
    0.69
     getters
    0.66
    getter
    0.56
     Getter
    0.50
     war
    0.47
     PVC
    0.46
     strict
    0.46
     pvc
    0.45
     LANC
    0.44
     Commit
    0.43
    Activations Density 0.002%

    No Known Activations