© 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. 106343
    Prev
    Next
    INDEX
    Explanations

    attach or attachment

    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
    »-
    -0.90
     fiore
    -0.86
    ἂ
    -0.79
     Réalisation
    -0.78
     Bengals
    -0.78
    ドル
    -0.77
    旨
    -0.76
    -</
    -0.76
     \<
    -0.75
     salts
    -0.75
    POSITIVE LOGITS
     przekon
    0.83
    分離
    0.81
    Attach
    0.79
     zapew
    0.79
     Attach
    0.76
     feasible
    0.75
     attaching
    0.73
     ATTACH
    0.73
    îte
    0.72
    äß
    0.71
    Activations Density 0.019%

    No Known Activations