© 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. 33167
    Prev
    Next
    INDEX
    Explanations

    can 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
    ificantly
    -0.89
    Done
    -0.82
     done
    -0.82
     după
    -0.81
    Iss
    -0.77
     liberally
    -0.77
    Gets
    -0.75
     PRODUC
    -0.75
     چیزی
    -0.75
     objec
    -0.74
    POSITIVE LOGITS
     ketika
    0.84
    continue
    0.84
     dezembro
    0.82
    raim
    0.81
    fier
    0.81
    ilst
    0.80
    mountable
    0.79
    asily
    0.79
     enfermedades
    0.79
    hopp
    0.78
    Activations Density 0.064%

    No Known Activations