© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 47892
    Prev
    Next
    INDEX
    Explanations

    source: and attribution

    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
    aried
    -1.08
    continue
    -0.90
    aving
    -0.90
    inOrder
    -0.87
    |;
    -0.85
     puntual
    -0.85
     מתח
    -0.85
    žem
    -0.85
     entusi
    -0.84
    nilai
    -0.84
    POSITIVE LOGITS
     own
    1.73
     based
    1.73
     adapted
    1.59
     created
    1.55
     derived
    1.36
     Adapted
    1.35
     constructed
    1.34
     compilation
    1.34
     compiled
    1.34
     drawn
    1.25
    Activations Density 0.005%

    No Known Activations