© 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. 63152
    Prev
    Next
    INDEX
    Explanations

    no warranty

    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
     but
    -2.86
     ولكن
    -1.38
     แต่
    -1.31
     لكن
    -1.30
     लेकिन
    -1.25
     zwar
    -1.23
     nhưng
    -1.20
     αλλά
    -1.12
     although
    -1.12
    だったが
    -1.09
    POSITIVE LOGITS
     nonetheless
    1.15
     tetap
    1.02
     trotzdem
    0.96
    still
    0.94
     nevertheless
    0.90
    仍
    0.90
    还是
    0.81
     still
    0.79
    其中
    0.79
    によると
    0.78
    Activations Density 0.070%

    No Known Activations