© 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. 72381
    Prev
    Next
    INDEX
    Explanations

    introducing reasons

    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
     reservado
    -1.14
    ナイ
    -1.08
     both
    -1.07
    ר
    -1.05
     cairan
    -1.04
     asisti
    -1.02
    เกี่ยว
    -0.99
    Ḃ
    -0.99
    र
    -0.98
     rígido
    -0.98
    POSITIVE LOGITS
     précédemment
    1.13
     Setelah
    1.13
     we
    1.13
     POSSIBLE
    1.10
    Emotion
    1.09
    になるので
    1.09
    DrawerToggle
    1.06
    elser
    1.05
    POSTS
    1.05
     possível
    1.04
    Activations Density 0.141%

    No Known Activations