© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 29884
    Prev
    Next
    INDEX
    Explanations

    state achieved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ORIGIN
    -0.88
     PLEAS
    -0.86
     Swal
    -0.80
     jedi
    -0.78
    пол
    -0.77
    endaftar
    -0.77
    uterie
    -0.76
    ነ
    -0.76
     Fulfillment
    -0.76
    ')";
    -0.75
    POSITIVE LOGITS
     achieved
    3.91
    achieved
    2.73
     attained
    2.63
     achieve
    2.41
     achievable
    2.31
    Achie
    2.28
     Achie
    2.22
     obtained
    2.08
     attainable
    2.02
     ensured
    1.96
    Activations Density 0.114%

    No Known Activations