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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12239
    Prev
    Next
    INDEX
    Explanations

    beauty, appearance, features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ymax
    -1.16
    FontAwesomeIcon
    -1.11
     хуже
    -1.10
    ]=
    -1.09
    pi
    -1.09
    之事
    -1.09
     for
    -1.08
     :=
    -1.07
    arch
    -1.07
     his
    -1.06
    POSITIVE LOGITS
     ویتامین
    1.71
     komment
    1.61
     kollek
    1.38
    eschön
    1.37
    டைய
    1.32
     Шаг
    1.28
    fotograf
    1.26
     jerawat
    1.25
    Referințe
    1.24
     llavero
    1.23
    Activations Density 0.033%

    No Known Activations