© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40299
    Prev
    Next
    INDEX
    Explanations

    software, legal, and narrative contexts

    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
    ñales
    -1.33
    PYX
    -1.27
    CCION
    -1.24
    xAA
    -1.24
    ㎎
    -1.22
     作り方
    -1.20
     provocó
    -1.20
    CCIÓN
    -1.20
     spise
    -1.18
    IFICACIÓN
    -1.15
    POSITIVE LOGITS
    乄
    1.22
    ㄋ
    1.20
     erhi
    1.20
    是怎么回事
    1.18
    ᛬
    1.16
    還能
    1.15
     pareti
    1.15
    嘍
    1.14
    </em>
    1.13
     offrir
    1.11
    Activations Density 0.098%

    No Known Activations