© 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. 205335
    Prev
    Next
    INDEX
    Explanations

    given on page

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

    system designing

    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
    Officer
    0.47
    Assertion
    0.46
    balancing
    0.46
    র্ডার
    0.46
    ostr
    0.45
    banding
    0.45
    Constraint
    0.45
    awner
    0.44
    𝐯
    0.44
    Brun
    0.44
    POSITIVE LOGITS
     acute
    0.58
     colleagues
    0.54
     hrs
    0.54
     manufactures
    0.53
     eradicate
    0.53
     ages
    0.52
     ups
    0.51
     colle
    0.49
     Acute
    0.49
     manuf
    0.49
    Activations Density 0.000%

    No Known Activations