© 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. 9586
    Prev
    Next
    INDEX
    Explanations

    heart hath

    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
    </em>
    -0.84
     Inhalten
    -0.81
     practica
    -0.81
    ಿಕ
    -0.80
     شہر
    -0.79
    frase
    -0.79
    苒
    -0.79
     שלה
    -0.79
    дьба
    -0.79
     خونه
    -0.77
    POSITIVE LOGITS
     isKindOfClass
    0.84
    ãn
    0.80
    ),
    0.75
     EdgeInsets
    0.75
    equalTo
    0.74
     Ré
    0.74
    cação
    0.73
    getMenuInflater
    0.73
    hw
    0.73
    циями
    0.73
    Activations Density 0.005%

    No Known Activations