© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73283
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns

    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
     گیاه
    -1.20
     nagu
    -1.20
     النبات
    -1.12
    ׇ
    -1.09
    []]
    -1.09
    ˄
    -1.08
    🥷
    -1.08
     mengakui
    -1.06
     الجلد
    -1.06
    鲮
    -1.04
    POSITIVE LOGITS
    ּוֹ
    1.63
    ַּ
    1.60
    וּ
    1.49
    ִּ
    1.47
    וֹ
    1.46
    🩹
    1.36
     nhung
    1.34
    ָּ
    1.33
     said
    1.32
     Thursday
    1.31
    Activations Density 0.001%

    No Known Activations