© 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. 59498
    Prev
    Next
    INDEX
    Explanations

    Pří kasus

    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
    ädigung
    -0.82
     typed
    -0.80
     +%
    -0.79
    現實
    -0.77
     Yer
    -0.77
     during
    -0.75
     Beide
    -0.75
    óság
    -0.75
     Journals
    -0.75
    nodeType
    -0.75
    POSITIVE LOGITS
     également
    0.84
    NIA
    0.83
     lecteur
    0.79
    陷
    0.77
    левой
    0.75
    ælde
    0.74
     PROBLE
    0.73
     advancement
    0.72
    Combine
    0.72
    偶
    0.70
    Activations Density 0.002%

    No Known Activations