© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 66655
    Prev
    Next
    INDEX
    Explanations

    metaphors to life situations

    np_acts-logits-general · gemini-2.5-flash-lite

    following descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bio
    0.46
     INR
    0.46
     Bio
    0.43
    :_
    0.43
     this
    0.39
     Amer
    0.38
     compress
    0.38
     ▪
    0.38
     geot
    0.38
     Mille
    0.38
    POSITIVE LOGITS
     metaphor
    0.68
     metaphorical
    0.61
     analogy
    0.55
     metaphors
    0.51
     பள்ளத்தா
    0.48
    馊
    0.44
     analogies
    0.44
    теше
    0.43
     усилия
    0.43
     краси
    0.43
    Activations Density 0.216%

    No Known Activations