© 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. 95700
    Prev
    Next
    INDEX
    Explanations

    heritage, electronic, social, sports, RPG, imaging, sustainability, inventory, media, environmental, metrics, inflammatory

    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
     with
    -1.41
     their
    -1.23
    多かった
    -1.13
     svært
    -1.13
     valamint
    -1.12
    ₱
    -1.10
    ieš
    -1.09
     würde
    -1.09
    他会
    -1.08
     nebo
    -1.07
    POSITIVE LOGITS
    Hermoso
    1.29
     is
    1.27
     意思
    1.20
    talking
    1.15
     Propiedad
    1.12
    헷
    1.10
    ❇
    1.10
     经典
    1.08
    捫
    1.07
    implemented
    1.05
    Activations Density 0.092%

    No Known Activations