© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 145211
    Prev
    Next
    INDEX
    Explanations

    emergency contacts, votes or salt

    np_acts-logits-general · gemini-2.5-flash-lite

    common phrases and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Furthermore
    0.43
    цька
    0.41
    বাড়
    0.40
    发布
    0.40
     Partie
    0.40
    Vad
    0.39
    kWh
    0.39
    婼
    0.39
    Vý
    0.38
    发布的
    0.38
    POSITIVE LOGITS
     tình
    0.50
    තාව
    0.47
    लेन
    0.46
     ут
    0.45
     înc
    0.45
    DomainMask
    0.45
     double
    0.45
     nirv
    0.44
    چان
    0.44
     souvent
    0.44
    Activations Density 0.001%

    No Known Activations