© 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. 14832
    Prev
    Next
    INDEX
    Explanations

    organizations and fields

    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
    ּוֹ
    -1.59
    ֶּ
    -1.38
    וּ
    -1.36
    ַּ
    -1.35
    וֹ
    -1.26
    hdashline
    -1.18
    baomidou
    -1.12
     ihrer
    -1.09
     robić
    -1.09
    simov
    -1.05
    POSITIVE LOGITS
    ׇ
    1.64
    Pendidikan
    1.26
    komme
    1.21
     investimentos
    1.19
     treff
    1.13
     animado
    1.12
     kommunik
    1.10
    Spesifikasi
    1.09
     tatuagens
    1.06
     visuelle
    1.06
    Activations Density 0.119%

    No Known Activations