© 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. 35720
    Prev
    Next
    INDEX
    Explanations

    text generation and translation

    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
    ‟
    -1.30
    𝗼
    -1.22
     during
    -1.18
    lede
    -1.15
    はこんな感じ
    -1.13
    TO
    -1.12
    水墨
    -1.12
    andExpect
    -1.11
    нович
    -1.10
    🏡
    -1.10
    POSITIVE LOGITS
     Що
    1.40
    ⠇
    1.35
     output
    1.30
    plantilla
    1.30
    ventana
    1.27
     생성
    1.27
     eccellente
    1.25
     versátil
    1.24
     femenina
    1.23
    楽しみに
    1.23
    Activations Density 0.021%

    No Known Activations