© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199031
    Prev
    Next
    INDEX
    Explanations

    significant impairments

    np_acts-logits-general · gemini-2.5-flash-lite

    urgent security claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Colonel
    0.54
     Client
    0.54
    GER
    0.49
    ClientSize
    0.46
     Acute
    0.45
     Citizenship
    0.45
     Causes
    0.45
     Mia
    0.45
    嬅
    0.45
     sufferings
    0.45
    POSITIVE LOGITS
     appli
    0.49
    ത
    0.47
     fixation
    0.46
    荇
    0.45
    дан
    0.44
     ಹಾಸ
    0.44
    딴
    0.44
     እድ
    0.43
    gegen
    0.43
    දන
    0.43
    Activations Density 0.001%

    No Known Activations