© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12090
    Prev
    Next
    INDEX
    Explanations

    back of, behind, backend

    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
     appelez
    0.57
     događ
    0.55
     yana
    0.55
     jis
    0.52
     différence
    0.52
     labios
    0.52
     în
    0.52
     ý
    0.52
     têm
    0.52
     nDims
    0.52
    POSITIVE LOGITS
    Back
    1.05
     Back
    1.04
    back
    1.02
    背
    1.00
     belakang
    0.99
     behind
    0.95
     背
    0.91
     الخلف
    0.91
     back
    0.90
     पीछे
    0.90
    Activations Density 0.051%

    No Known Activations