© 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. 83432
    Prev
    Next
    INDEX
    Explanations

    government or organizational titles

    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
     del
    -1.09
     F
    -1.05
     de
    -1.03
     G
    -1.01
     O
    -1.01
     M
    -0.99
     s
    -0.98
     L
    -0.96
     La
    -0.95
     several
    -0.94
    POSITIVE LOGITS
    が無い
    1.20
     reager
    1.20
     hemd
    1.15
     zei
    1.09
     tslint
    1.08
     zoude
    1.08
     土豆
    1.07
    穽
    1.06
    reh
    1.03
     aussit
    1.03
    Activations Density 0.164%

    No Known Activations