© 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. 40-GEMMASCOPE-2-RES-65K
    7. 47768
    Prev
    Next
    INDEX
    Explanations

    Bloom's Taxonomy and bloom coating

    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_40_width_65k_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
     foot
    0.88
    foot
    0.73
    Foot
    0.71
     Foot
    0.70
     feet
    0.68
    footed
    0.67
     footer
    0.65
    脚
    0.64
    feet
    0.63
     Feet
    0.61
    POSITIVE LOGITS
     Bloom
    0.97
    Bloom
    0.90
     bloom
    0.89
     blooms
    0.84
     Blooms
    0.82
    bloom
    0.78
     BLO
    0.70
    blo
    0.64
     recall
    0.63
    Blo
    0.62
    Activations Density 0.039%

    No Known Activations