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. 547
    Prev
    Next
    INDEX
    Explanations

    war and crisis

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

    wars and revolutions

    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
    ”
    0.66
    ä
    0.65
    le
    0.56
    с
    0.55
    ills
    0.55
    d
    0.55
    i
    0.54
    ently
    0.53
    án
    0.53
    ate
    0.52
    POSITIVE LOGITS
     ascenso
    0.59
    {
    0.55
    અ
    0.52
     OPPORT
    0.51
     ouverte
    0.50
     Eles
    0.50
     tecnológico
    0.50
     étape
    0.50
     Warsz
    0.50
     intérieur
    0.49
    Activations Density 0.986%

    No Known Activations