© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    newly identified candidates

    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
    AXIS
    -0.81
    ärin
    -0.81
    MapView
    -0.75
    енная
    -0.75
    Produto
    -0.74
     oceans
    -0.74
     vanille
    -0.73
    Pid
    -0.73
    анта
    -0.72
     tournage
    -0.72
    POSITIVE LOGITS
     identification
    1.26
     counterpart
    1.16
     identified
    1.14
     identific
    1.06
     candidate
    1.06
     Identified
    1.02
     Identification
    1.02
     candidates
    0.99
     counterparts
    0.94
     identificado
    0.93
    Activations Density 0.046%

    No Known Activations