Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7794
    Prev
    Next
    INDEX
    Explanations

    forms of stand

    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
     hörte
    -0.94
     übernahm
    -0.92
     folgte
    -0.88
     zeigte
    -0.88
     fühlte
    -0.85
     brachte
    -0.83
     lebte
    -0.83
     suchte
    -0.82
     arbeitete
    -0.82
     hielt
    -0.79
    POSITIVE LOGITS
     stand
    6.78
     stands
    6.63
     standing
    6.19
     stood
    5.84
     STAND
    5.63
    Standing
    5.22
    Stand
    5.19
     Stand
    5.13
    stands
    5.03
    stand
    5.00
    Activations Density 0.183%

    No Known Activations