© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27459
    Prev
    Next
    INDEX
    Explanations

    turning, shines, rotates, sticks, cut, fits, pulled, pushes, drives

    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
    ֶּ
    -2.06
    ּוֹ
    -1.91
    ִּ
    -1.64
    ַּ
    -1.59
    ְּ
    -1.58
    ֵּ
    -1.52
     السياس
    -1.52
     Sahne
    -1.48
     kulinar
    -1.47
     стомато
    -1.46
    POSITIVE LOGITS
     chré
    1.59
     ἄ
    1.45
     ادبی
    1.34
     ilustrasi
    1.33
     chrétienne
    1.29
    ícias
    1.28
     الجلد
    1.26
     οὐ
    1.23
    licante
    1.23
    fordable
    1.21
    Activations Density 0.288%

    No Known Activations