© 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. 76000
    Prev
    Next
    INDEX
    Explanations

    fruit and garden concepts

    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
     ජ
    0.42
     כמ
    0.42
     ማ
    0.41
    nier
    0.41
     keluar
    0.41
     finale
    0.40
    terior
    0.40
     ሁ
    0.40
    -'+
    0.40
    irteenth
    0.39
    POSITIVE LOGITS
     Been
    0.51
    marginX
    0.47
     Uber
    0.43
     Their
    0.41
     museums
    0.40
     имеются
    0.40
    各类
    0.40
    repositories
    0.40
     BEEN
    0.39
     Qxb
    0.39
    Activations Density 0.012%

    No Known Activations