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-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 794
    Prev
    Next
    INDEX
    Explanations

    qualities of success and character

    np_acts-logits-general · gemini-2.5-flash-lite

    calm and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    v
    0.78
    h
    0.70
    imming
    0.54
    ugg
    0.52
    ukung
    0.50
    ide
    0.50
    드는
    0.50
    hrm
    0.50
    ummy
    0.48
    inians
    0.48
    POSITIVE LOGITS
     İlk
    0.61
    ې
    0.58
    andı
    0.55
     Fluss
    0.55
     Freiheit
    0.54
     İl
    0.53
     Mapa
    0.53
     Distrito
    0.52
     Ij
    0.52
     Presidente
    0.51
    Activations Density 0.584%

    No Known Activations