© 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. 224848
    Prev
    Next
    INDEX
    Explanations

    iconic food, heal heartbreak, batteries, microwave

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

    listen what you have in mind

    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
    ന്ന
    0.54
    𝚐
    0.50
     apare
    0.48
     ခု
    0.47
    ogén
    0.47
    RECE
    0.46
     encuentre
    0.46
     escolares
    0.46
    Número
    0.46
     うん
    0.46
    POSITIVE LOGITS
    0
    0.50
     Sap
    0.47
     SAP
    0.47
     CNR
    0.46
     Viking
    0.45
     sap
    0.45
     suitable
    0.44
     Laws
    0.44
     Cor
    0.44
     Gy
    0.44
    Activations Density 0.000%

    No Known Activations