© 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. 22-GEMMASCOPE-RES-131K
    7. 128337
    Prev
    Next
    INDEX
    Explanations

    it up

    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
    该如何
    -1.12
     moteurs
    -1.09
     pakan
    -1.06
    蕺
    -1.05
     justifyContent
    -1.05
    过去了
    -1.05
     TreeSet
    -1.05
     marginBottom
    -1.04
    angnya
    -1.01
    Kus
    -1.01
    POSITIVE LOGITS
     your
    2.27
     yourself
    2.08
     yourselves
    1.47
     now
    1.30
     сейчас
    1.22
     ולה
    1.20
    你的
    1.18
     valami
    1.09
     gärna
    1.07
     男孩
    1.06
    Activations Density 0.097%

    No Known Activations