© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77166
    Prev
    Next
    INDEX
    Explanations

    go on to

    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
    üf
    -0.79
    やってきた
    -0.75
    poel
    -0.74
    waktu
    -0.73
    Kali
    -0.71
    nova
    -0.71
    िज
    -0.71
     Estados
    -0.71
     neue
    -0.70
    ってきました
    -0.69
    POSITIVE LOGITS
     went
    4.28
     go
    3.64
     goes
    3.30
    Went
    3.02
    ไป
    2.72
    went
    2.72
     going
    2.47
     Went
    2.44
    goto
    2.31
     gone
    2.31
    Activations Density 0.082%

    No Known Activations