© 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. 219736
    Prev
    Next
    INDEX
    Explanations

    Mars

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

    Virtual Reality

    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
    ly
    0.49
    ilas
    0.48
     Künst
    0.46
     incididunt
    0.45
    であった
    0.45
     definisi
    0.44
     通
    0.43
     verwenden
    0.43
    ڈین
    0.42
     คุณ
    0.42
    POSITIVE LOGITS
     questionnaires
    0.50
     lawns
    0.47
    ড়ায়
    0.45
     flyers
    0.45
     wearables
    0.45
     streamers
    0.44
     hairdryer
    0.43
     powders
    0.43
     medallions
    0.42
    穩
    0.42
    Activations Density 0.000%

    No Known Activations