© 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. 10-GEMMASCOPE-RES-131K
    7. 75643
    Prev
    Next
    INDEX
    Explanations

    now and then statements

    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_10/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
     of
    -1.73
    </em>
    -1.70
    1
    -1.68
    (
    -1.59
     $
    -1.52
    ”
    -1.48
    -
    -1.44
     —
    -1.37
    ,
    -1.37
     caricatura
    -1.35
    POSITIVE LOGITS
     you
    1.98
    ulitis
    1.66
     dalamnya
    1.60
    entown
    1.57
     później
    1.49
    atized
    1.48
     entera
    1.48
     fuese
    1.45
    ,​
    1.41
    ěji
    1.40
    Activations Density 0.025%

    No Known Activations