© 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. 63359
    Prev
    Next
    INDEX
    Explanations

    actions, processes, verbs

    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
    nya
    -1.10
    อย่าง
    -1.09
    อาจ
    -1.01
    ѓ
    -1.00
    rent
    -0.98
     same
    -0.98
    อีก
    -0.96
    い
    -0.92
    ны
    -0.91
    こと
    -0.91
    POSITIVE LOGITS
    女孩子
    1.01
    ments
    0.97
    しては
    0.90
     inš
    0.89
    iado
    0.89
     turístico
    0.87
    下一篇
    0.86
     vaš
    0.85
    شكرا
    0.85
    षण
    0.85
    Activations Density 0.104%

    No Known Activations