© 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. 12184
    Prev
    Next
    INDEX
    Explanations

    We have

    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
    }}%
    -0.80
    Suit
    -0.77
    ebenarnya
    -0.77
    adari
    -0.75
     même
    -0.75
     reusable
    -0.74
     Hệ
    -0.74
    apkan
    -0.74
     occupied
    -0.73
     Væ
    -0.73
    POSITIVE LOGITS
     NUE
    0.73
     Saya
    0.73
     GCP
    0.72
     Wikiped
    0.71
    Saya
    0.71
     says
    0.70
     Yorker
    0.70
     AED
    0.69
    Kako
    0.69
    signUp
    0.68
    Activations Density 0.022%

    No Known Activations