© 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. 71074
    Prev
    Next
    INDEX
    Explanations

    war, rankings, stimulus, location, cyber

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

    fear, worry, death, murder

    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
    嘜
    0.48
     پال
    0.48
    ими
    0.47
     novedad
    0.46
     instytuc
    0.46
     novedades
    0.45
     nouve
    0.45
     idiomas
    0.45
    𝙋
    0.45
     iniciativas
    0.44
    POSITIVE LOGITS
     I
    0.46
     Prasad
    0.42
     Death
    0.40
     Peace
    0.40
    ermat
    0.40
    pus
    0.40
    uki
    0.39
     Roh
    0.39
     Dev
    0.39
     Lea
    0.39
    Activations Density 0.000%

    No Known Activations