© 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. 28062
    Prev
    Next
    INDEX
    Explanations

    assigned using

    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
    (=
    -0.94
    ichts
    -0.89
    义务
    -0.85
    aduras
    -0.85
    aufen
    -0.84
    Plat
    -0.84
     Wisdom
    -0.82
    プレー
    -0.81
     qualquer
    -0.80
     pages
    -0.79
    POSITIVE LOGITS
     difficult
    1.59
     Difficult
    1.40
     siker
    1.34
    difficulty
    1.32
    difficult
    1.30
    ยาก
    1.29
     attempt
    1.27
     Attempt
    1.24
     difficulty
    1.23
    Attempts
    1.22
    Activations Density 0.128%

    No Known Activations