© 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. 33454
    Prev
    Next
    INDEX
    Explanations

    creating things

    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
    )="
    -1.36
     repuesto
    -1.34
     carcasa
    -1.30
     οποία
    -1.25
     Ucraina
    -1.23
     aumentando
    -1.21
    vinte
    -1.20
    耵
    -1.20
     autonomie
    -1.20
    が可能
    -1.20
    POSITIVE LOGITS
     from
    3.09
     with
    3.08
     in
    2.69
     without
    2.67
     through
    2.25
     only
    2.22
     using
    2.08
     at
    2.06
     for
    2.05
     across
    2.05
    Activations Density 0.250%

    No Known Activations