© 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. 72038
    Prev
    Next
    INDEX
    Explanations

    mathematical calculation or question definition

    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
    Lugares
    -1.13
     ᾿
    -1.11
     such
    -1.08
     divertida
    -1.05
    
    -1.05
    domaine
    -1.04
     equipa
    -1.03
     ferie
    -1.02
    informe
    -1.02
    dateien
    -1.02
    POSITIVE LOGITS
    }}{
    1.43
     for
    1.30
    いただけます
    1.20
     теперь
    1.20
     now
    1.20
    〉
    1.18
     ahora
    1.17
     if
    1.16
     alternative
    1.15
    dius
    1.14
    Activations Density 0.003%

    No Known Activations