© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8357
    Prev
    Next
    INDEX
    Explanations

    metaphors and analogies

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

    metaphorical language

    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_53_width_65k_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
     محور
    0.43
     etc
    0.40
    etc
    0.40
     выполнить
    0.40
     peny
    0.40
    などを
    0.39
    ///////////
    0.39
    یں۔
    0.38
    _^
    0.38
     undergo
    0.38
    POSITIVE LOGITS
     metaphorical
    1.06
     metaphor
    1.03
     figuratively
    0.86
     metaphors
    0.85
     proverbial
    0.82
     figurative
    0.72
     analogy
    0.65
     spiritually
    0.56
    般的
    0.54
    figur
    0.54
    Activations Density 0.175%

    No Known Activations