© 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. 28414
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculus

    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
     schme
    -0.81
    經歷
    -0.81
     ï
    -0.79
     Надо
    -0.78
    arques
    -0.78
    psons
    -0.77
    LoadScene
    -0.77
     Multil
    -0.77
    lenz
    -0.75
    alarme
    -0.75
    POSITIVE LOGITS
     palsy
    0.83
     wią
    0.82
     afge
    0.81
    schöne
    0.81
    tière
    0.80
    Hades
    0.80
     pintor
    0.79
    蔭
    0.79
     brugt
    0.78
     aanz
    0.77
    Activations Density 0.057%

    No Known Activations