© 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. 38236
    Prev
    Next
    INDEX
    Explanations

    Model Railways, The Internet, rotateGun

    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
    וּ
    -1.95
    וֹ
    -1.49
    ּוֹ
    -1.42
    ῤ
    -1.22
    וּ
    -1.21
    ְר
    -1.20
    וֹ
    -1.19
     opção
    -1.13
     extensão
    -1.09
    ־ה
    -1.09
    POSITIVE LOGITS
    ༼
    1.32
     princesas
    1.27
     patata
    1.20
    ığımız
    1.10
    ׇ
    1.09
     fundamentos
    1.09
    recent
    1.09
     eccl
    1.06
    CCIÓN
    1.05
     блюдо
    1.05
    Activations Density 0.005%

    No Known Activations