© 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. 208829
    Prev
    Next
    INDEX
    Explanations

    machine, tube, bending, computer

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

    states, refers, discusses abstract concepts

    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
     хозя
    0.50
    ."]
    0.50
     সেন্টার
    0.47
    ধ্যে
    0.47
    +'-
    0.47
    会导致
    0.46
    ಗೂ
    0.45
    ]).
    0.44
     الجديد
    0.44
    ]&
    0.44
    POSITIVE LOGITS
     pardon
    0.52
     Jon
    0.50
     State
    0.48
     Don
    0.48
     Everyone
    0.47
     veut
    0.47
     You
    0.47
     Chuck
    0.46
     Every
    0.46
    afon
    0.46
    Activations Density 0.001%

    No Known Activations