© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26202
    Prev
    Next
    INDEX
    Explanations

    names following quotes or colons

    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
     sejak
    -1.24
     romantis
    -1.11
     minori
    -1.09
     indien
    -1.04
     camere
    -1.03
    ~/
    -1.03
     murale
    -1.02
    шивания
    -1.02
    konos
    -1.01
    虽然
    -0.99
    POSITIVE LOGITS
     of
    1.61
     who
    1.20
    謳
    1.18
     koruyucu
    1.04
     at
    1.04
    相应的
    1.03
     whose
    1.02
     into
    1.02
    復興
    1.02
     aprendizagem
    1.01
    Activations Density 0.005%

    No Known Activations