© 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. 34-GEMMASCOPE-RES-131K
    4. 118724
    Prev
    Next
    INDEX
    Explanations

    can followed by verbs

    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
    vegli
    -1.04
     klarer
    -0.91
     investigate
    -0.88
    学的
    -0.87
    amá
    -0.84
     align
    -0.83
    jame
    -0.83
     năm
    -0.82
     another
    -0.82
     revered
    -0.82
    POSITIVE LOGITS
     because
    0.91
     lynch
    0.90
     römischen
    0.90
     не
    0.89
     Россий
    0.87
     Beatles
    0.87
     tidak
    0.85
    唔係
    0.85
    cja
    0.84
    менно
    0.83
    Activations Density 0.029%

    No Known Activations