© 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. 64920
    Prev
    Next
    INDEX
    Explanations

    brand names and entities

    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
    montage
    -1.28
    -1.27
    kkk
    -1.27
    uits
    -1.27
    dienne
    -1.26
    pans
    -1.26
    usive
    -1.24
    -1.23
    ogues
    -1.22
    umers
    -1.21
    POSITIVE LOGITS
     beschä
    1.24
     ofrecemos
    1.24
     annehmen
    1.20
    さんも
    1.19
     revolutionary
    1.14
     всегда
    1.13
    érez
    1.13
     horribly
    1.09
     groundbreaking
    1.09
     creates
    1.09
    Activations Density 0.193%

    No Known Activations