© 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. 62460
    Prev
    Next
    INDEX
    Explanations

    doing their best

    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
    mine
    -0.96
    ╹
    -0.80
    rr
    -0.80
    desired
    -0.79
    wand
    -0.79
    frost
    -0.78
    itself
    -0.77
    voiture
    -0.77
    Mine
    -0.77
    риста
    -0.76
    POSITIVE LOGITS
     my
    1.94
     their
    1.81
     our
    1.80
     his
    1.58
     your
    1.56
     best
    1.40
     its
    1.30
     свою
    1.20
    best
    1.16
     своего
    1.15
    Activations Density 0.021%

    No Known Activations