© 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. 198118
    Prev
    Next
    INDEX
    Explanations

    watermark or 🤩? brands are a world of

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

    showing enslaved status

    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
     startDate
    0.54
     récupérer
    0.53
     médicaments
    0.52
    рное
    0.52
    િર
    0.52
     intégral
    0.52
    ὗ
    0.52
     idempot
    0.51
    าก
    0.50
    王
    0.50
    POSITIVE LOGITS
    BERT
    0.55
     بما
    0.50
    dining
    0.49
    FOR
    0.48
    dispose
    0.48
    Hu
    0.47
    a
    0.47
    OUT
    0.47
    typ
    0.47
    diffusion
    0.46
    Activations Density 0.000%

    No Known Activations