© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55696
    Prev
    Next
    INDEX
    Explanations

    abstract/physical properties and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ق
    0.55
    م
    0.54
     SPINE
    0.52
    놁
    0.51
     ब्रैकेट
    0.51
    솔
    0.50
    翼
    0.49
    妘
    0.49
    Пу
    0.48
    გუფი
    0.48
    POSITIVE LOGITS
    ized
    0.53
     invasive
    0.52
    riminate
    0.51
     intrusion
    0.50
     physical
    0.46
     spectroscopy
    0.46
     tangible
    0.46
     intrusive
    0.46
     harrowing
    0.45
     radiating
    0.44
    Activations Density 0.001%

    No Known Activations