© 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. 109633
    Prev
    Next
    INDEX
    Explanations

    models and data

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

    molecules and atoms

    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
     $)$
    0.52
     incarceration
    0.48
     ένα
    0.48
     checkFor
    0.48
    developed
    0.47
     amassed
    0.47
     lessening
    0.46
     wellbeing
    0.46
     vibe
    0.46
     patty
    0.45
    POSITIVE LOGITS
     modelos
    0.48
    {
    0.48
     النموذج
    0.47
     模型
    0.46
     modele
    0.46
    0.45
    的模型
    0.44
    จะไม่
    0.43
    /
    0.43
    த்
    0.43
    Activations Density 0.000%

    No Known Activations