© 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. 76093
    Prev
    Next
    INDEX
    Explanations

    java import android androidx

    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
     some
    -1.29
     one
    -1.21
     any
    -1.16
     weird
    -1.12
     Some
    -1.10
     unusual
    -1.10
     all
    -1.09
     out
    -1.06
     truly
    -1.02
     (
    -1.01
    POSITIVE LOGITS
     Dinas
    1.13
     nerfs
    1.11
     pensamientos
    1.10
    沵
    1.05
    /
    1.04
     Poincar
    1.04
     betreffenden
    1.03
    
    1.03
     tamaños
    1.01
     """
    1.01
    Activations Density 0.058%

    No Known Activations