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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66135
    Prev
    Next
    INDEX
    Explanations

    role or name

    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
     ministra
    -1.34
    致力
    -1.31
     europea
    -1.27
     ungefär
    -1.23
     only
    -1.23
     not
    -1.23
     certainly
    -1.22
     trofeo
    -1.20
    疾病
    -1.20
     irrespective
    -1.16
    POSITIVE LOGITS
     savag
    1.46
     Flüssigkeit
    1.41
     captiv
    1.35
     luzes
    1.34
     jeugd
    1.32
     Wikime
    1.29
     poign
    1.28
    太过
    1.27
     られる
    1.27
     fervent
    1.26
    Activations Density 0.283%

    No Known Activations