© 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. 10-GEMMASCOPE-RES-131K
    7. 20675
    Prev
    Next
    INDEX
    Explanations

    legal claims and compensation

    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
     anyag
    -1.21
    TIPOS
    -1.18
    回到了
    -1.14
    </b>
    -1.13
     eſ
    -1.09
    Perth
    -1.09
     regresó
    -1.08
    狲
    -1.06
     llegará
    -1.05
    姈
    -1.05
    POSITIVE LOGITS
     this
    1.20
    QMetaType
    1.17
    いただきます
    1.13
    imente
    1.08
    頂き
    1.07
    Ḍ
    1.04
    kommer
    1.02
    多少钱
    1.01
     well
    1.00
     case
    1.00
    Activations Density 0.032%

    No Known Activations