© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60533
    Prev
    Next
    INDEX
    Explanations

    famous figures used metaphorically

    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_34/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
    usually
    -1.35
    often
    -1.23
    就跟
    -1.14
    ほんと
    -1.08
     crucial
    -1.07
    ari
    -1.06
     …
    -1.05
    el
    -1.05
     focuses
    -1.03
     verschied
    -1.02
    POSITIVE LOGITS
     or
    1.72
     type
    1.66
     vagy
    1.27
    lanmış
    1.17
    dalam
    1.17
     circa
    1.16
     esque
    1.16
     یا
    1.11
     或
    1.10
    type
    1.08
    Activations Density 0.065%

    No Known Activations