© 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. 22-GEMMASCOPE-RES-131K
    4. 41
    Prev
    Next
    INDEX
    Explanations

    Experimental studies

    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
     these
    -0.98
    teth
    -0.94
    thenia
    -0.88
     Beleuchtung
    -0.87
     már
    -0.86
    epy
    -0.83
    quot
    -0.81
     those
    -0.80
    ês
    -0.79
    рование
    -0.79
    POSITIVE LOGITS
    écrire
    1.09
    앓
    1.01
     prouver
    1.01
     NTIS
    0.99
     mended
    0.94
    σαι
    0.93
    lihatkan
    0.92
     nears
    0.91
     chacune
    0.91
     brill
    0.90
    Activations Density 0.000%

    No Known Activations