© 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. 10-GEMMASCOPE-RES-131K
    7. 44529
    Prev
    Next
    INDEX
    Explanations

    model modelmodel and product numbers

    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_10/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
     Pokud
    -1.55
     into
    -1.41
    РЭ
    -1.38
    puerta
    -1.38
     joão
    -1.35
     deberían
    -1.35
    demás
    -1.34
    我才
    -1.34
     according
    -1.33
     migliore
    -1.33
    POSITIVE LOGITS
    </h3>
    1.35
    𝐬
    1.28
     typy
    1.26
    ValueGeneration
    1.24
     подготовка
    1.23
     and
    1.23
    SizeMode
    1.23
    ⤵
    1.20
     personalización
    1.20
    UTC
    1.19
    Activations Density 0.072%

    No Known Activations