© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78137
    Prev
    Next
    INDEX
    Explanations

    PRNewswire /

    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
    Not in Any Lists

    No Comments

    Negative Logits
     receptionist
    -0.69
    Lieu
    -0.68
    augmentation
    -0.66
    楽しみに
    -0.65
     pieni
    -0.65
     cleared
    -0.65
     concealment
    -0.64
    ובי
    -0.64
     Insect
    -0.64
    衡
    -0.64
    POSITIVE LOGITS
     Chia
    0.75
    ligere
    0.73
    BackColor
    0.73
    anity
    0.73
    gnano
    0.72
    urlopen
    0.72
    agents
    0.71
    fy
    0.71
    ilova
    0.70
    tamide
    0.70
    Activations Density 0.058%

    No Known Activations