© 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. 22-GEMMASCOPE-RES-131K
    7. 80065
    Prev
    Next
    INDEX
    Explanations

    always and sometimes

    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_22/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
     was
    -1.74
    可能會
    -1.15
     estaba
    -1.15
    crizione
    -1.12
     drew
    -1.12
     será
    -1.11
    店で
    -1.11
    なかったので
    -1.08
     może
    -1.07
     pfle
    -1.07
    POSITIVE LOGITS
     always
    2.58
     всегда
    2.09
     usually
    2.06
     תמיד
    2.03
     vždy
    2.00
     alltid
    1.98
    Always
    1.91
     often
    1.89
     sometimes
    1.81
    always
    1.75
    Activations Density 0.006%

    No Known Activations