© 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. 89883
    Prev
    Next
    INDEX
    Explanations

    selecting for output

    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
    wob
    -1.09
    graffiti
    -1.04
    immobili
    -1.04
    mika
    -1.04
    lemish
    -1.02
     adhesivo
    -0.99
    waw
    -0.98
     tuturor
    -0.98
    又一次
    -0.98
     cerámica
    -0.98
    POSITIVE LOGITS
    การ
    1.17
    主要的
    0.94
     进行
    0.89
    When
    0.86
    での
    0.84
    PG
    0.82
    ในการ
    0.82
     attempted
    0.79
    been
    0.78
    にします
    0.78
    Activations Density 0.328%

    No Known Activations