© 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. 204492
    Prev
    Next
    INDEX
    Explanations

    Representing things or relationships

    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
    nya
    0.50
    龋
    0.48
     cannot
    0.45
     sio
    0.45
     needs
    0.45
     idios
    0.44
     sient
    0.44
    Ū
    0.43
    管控
    0.43
    Campe
    0.43
    POSITIVE LOGITS
     és
    0.52
     ή
    0.47
     અને
    0.46
     và
    0.43
    ंना
    0.43
    ği
    0.42
    วัด
    0.42
     hoặc
    0.42
     και
    0.41
    মন্দ
    0.41
    Activations Density 0.001%

    No Known Activations